Merge commit 'v2.6.31-rc7' into x86/cpu

44 files changed, 2545 insertions, 1421 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 71830ba7b986..fe5f674d7a7d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -128,11 +128,11 @@ config SPARSEMEM_VMEMMAP
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
-	depends on HOTPLUG && !HIBERNATION && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC64 || SUPERH || S390)
 
 comment "Memory hotplug is currently incompatible with Software Suspend"
-	depends on SPARSEMEM && HOTPLUG && HIBERNATION
+	depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
@@ -203,25 +203,13 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
-config UNEVICTABLE_LRU
-	bool "Add LRU list to track non-evictable pages"
-	default y
-	help
-	  Keeps unevictable pages off of the active and inactive pageout
-	  lists, so kswapd will not waste CPU time or have its balancing
-	  algorithms thrown off by scanning these pages.  Selecting this
-	  will use one page flag and increase the code size a little,
-	  say Y unless you know what you are doing.
-
-	  See Documentation/vm/unevictable-lru.txt for more information.
-
 config HAVE_MLOCK
 	bool
 	default y if MMU=y
 
 config HAVE_MLOCKED_PAGE_BIT
 	bool
-	default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y
+	default y if HAVE_MLOCK=y
 
 config MMU_NOTIFIER
 	bool
@@ -237,9 +225,9 @@ config DEFAULT_MMAP_MIN_ADDR
 	  For most ia64, ppc64 and x86 users with lots of address space
 	  a value of 65536 is reasonable and should cause no problems.
 	  On arm and other archs it should not be higher than 32768.
-	  Programs which use vm86 functionality would either need additional
-	  permissions from either the LSM or the capabilities module or have
-	  this protection disabled.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need CAP_SYS_RAWIO or disable this
+	  protection by setting the value to 0.
 
 	  This value can be changed after boot using the
 	  /proc/sys/vm/mmap_min_addr tunable.
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index bb01e298f260..aa99fd1f7109 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -2,6 +2,7 @@ config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	depends on !HIBERNATION || !PPC && !SPARC
+	depends on !KMEMCHECK
 	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
 	  This results in a large slowdown, but helps to find certain types
diff --git a/mm/Makefile b/mm/Makefile
index e89acb090b4d..5e0bd6426693 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -12,6 +12,7 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o $(mmu-y)
+obj-y += init-mm.o
 
 obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o
@@ -27,6 +28,7 @@ obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
+obj-$(CONFIG_KMEMCHECK) += kmemcheck.o
 obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468a5035..c86edd244294 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
 
-
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum bdi_state bit;
@@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested);
 
 /**
  * congestion_wait - wait for a backing_dev to become uncongested
- * @rw: READ or WRITE
+ * @sync: SYNC or ASYNC IO
  * @timeout: timeout in jiffies
  *
  * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
  * write congestion.  If no backing_devs are congested then just wait for the
  * next write to be completed.
  */
-long congestion_wait(int rw, long timeout)
+long congestion_wait(int sync, long timeout)
 {
 	long ret;
 	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = io_schedule_timeout(timeout);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 282df0a09e6f..701740c9e81b 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -12,6 +12,7 @@
 #include <linux/pfn.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
+#include <linux/kmemleak.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -335,6 +336,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 {
 	unsigned long start, end;
 
+	kmemleak_free_part(__va(physaddr), size);
+
 	start = PFN_UP(physaddr);
 	end = PFN_DOWN(physaddr + size);
 
@@ -354,6 +357,8 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 	unsigned long start, end;
 
+	kmemleak_free_part(__va(addr), size);
+
 	start = PFN_UP(addr);
 	end = PFN_DOWN(addr + size);
 
@@ -516,6 +521,7 @@ find_block:
 		region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
 				start_off);
 		memset(region, 0, size);
+		kmemleak_alloc(region, size, 1, 0);
 		return region;
 	}
 
@@ -536,11 +542,15 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 		return kzalloc(size, GFP_NOWAIT);
 
 #ifdef CONFIG_HAVE_ARCH_BOOTMEM
-	bootmem_data_t *p_bdata;
-
-	p_bdata = bootmem_arch_preferred_node(bdata, size, align, goal, limit);
-	if (p_bdata)
-		return alloc_bootmem_core(p_bdata, size, align, goal, limit);
+	{
+		bootmem_data_t *p_bdata;
+
+		p_bdata = bootmem_arch_preferred_node(bdata, size, align,
+							goal, limit);
+		if (p_bdata)
+			return alloc_bootmem_core(p_bdata, size, align,
+							goal, limit);
+	}
 #endif
 	return NULL;
 }
diff --git a/mm/bounce.c b/mm/bounce.c
index 4ebe3ea83795..a2b76a588e34 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
-#include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
 #include <trace/events/block.h>
diff --git a/mm/dmapool.c b/mm/dmapool.c
index b1f0885dda22..3df063706f53 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -86,10 +86,12 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf)
 		unsigned pages = 0;
 		unsigned blocks = 0;
 
+		spin_lock_irq(&pool->lock);
 		list_for_each_entry(page, &pool->page_list, page_list) {
 			pages++;
 			blocks += page->in_use;
 		}
+		spin_unlock_irq(&pool->lock);
 
 		/* per-pool info, no real statistics yet */
 		temp = scnprintf(next, size, "%-16s %4u %4Zu %4Zu %2u\n",
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 54a0f8040afa..e43359214f6f 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -101,7 +101,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		
 		ret = force_page_cache_readahead(mapping, file,
 				start_index,
-				max_sane_readahead(nrpages));
+				nrpages);
 		if (ret > 0)
 			ret = 0;
 		break;
diff --git a/mm/filemap.c b/mm/filemap.c
index 1b60f30cebfa..ccea3b665c12 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -521,7 +521,7 @@ struct page *__page_cache_alloc(gfp_t gfp)
 {
 	if (cpuset_do_page_mem_spread()) {
 		int n = cpuset_mem_spread_node();
-		return alloc_pages_node(n, gfp, 0);
+		return alloc_pages_exact_node(n, gfp, 0);
 	}
 	return alloc_pages(gfp, 0);
 }
@@ -1004,9 +1004,6 @@ EXPORT_SYMBOL(grab_cache_page_nowait);
 static void shrink_readahead_size_eio(struct file *filp,
 					struct file_ra_state *ra)
 {
-	if (!ra->ra_pages)
-		return;
-
 	ra->ra_pages /= 4;
 }
 
@@ -1390,8 +1387,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
 		return -EINVAL;
 
-	force_page_cache_readahead(mapping, filp, index,
-					max_sane_readahead(nr));
+	force_page_cache_readahead(mapping, filp, index, nr);
 	return 0;
 }
 
@@ -1457,6 +1453,73 @@ static int page_cache_read(struct file *file, pgoff_t offset)
 
 #define MMAP_LOTSAMISS  (100)
 
+/*
+ * Synchronous readahead happens when we don't even find
+ * a page in the page cache at all.
+ */
+static void do_sync_mmap_readahead(struct vm_area_struct *vma,
+				   struct file_ra_state *ra,
+				   struct file *file,
+				   pgoff_t offset)
+{
+	unsigned long ra_pages;
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (VM_RandomReadHint(vma))
+		return;
+
+	if (VM_SequentialReadHint(vma) ||
+			offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) {
+		page_cache_sync_readahead(mapping, ra, file, offset,
+					  ra->ra_pages);
+		return;
+	}
+
+	if (ra->mmap_miss < INT_MAX)
+		ra->mmap_miss++;
+
+	/*
+	 * Do we miss much more than hit in this file? If so,
+	 * stop bothering with read-ahead. It will only hurt.
+	 */
+	if (ra->mmap_miss > MMAP_LOTSAMISS)
+		return;
+
+	/*
+	 * mmap read-around
+	 */
+	ra_pages = max_sane_readahead(ra->ra_pages);
+	if (ra_pages) {
+		ra->start = max_t(long, 0, offset - ra_pages/2);
+		ra->size = ra_pages;
+		ra->async_size = 0;
+		ra_submit(ra, mapping, file);
+	}
+}
+
+/*
+ * Asynchronous readahead happens when we find the page and PG_readahead,
+ * so we want to possibly extend the readahead further..
+ */
+static void do_async_mmap_readahead(struct vm_area_struct *vma,
+				    struct file_ra_state *ra,
+				    struct file *file,
+				    struct page *page,
+				    pgoff_t offset)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (VM_RandomReadHint(vma))
+		return;
+	if (ra->mmap_miss > 0)
+		ra->mmap_miss--;
+	if (PageReadahead(page))
+		page_cache_async_readahead(mapping, ra, file,
+					   page, offset, ra->ra_pages);
+}
+
 /**
  * filemap_fault - read in file data for page fault handling
  * @vma:	vma in which the fault was taken
@@ -1476,78 +1539,44 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
+	pgoff_t offset = vmf->pgoff;
 	struct page *page;
 	pgoff_t size;
-	int did_readaround = 0;
 	int ret = 0;
 
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (vmf->pgoff >= size)
+	if (offset >= size)
 		return VM_FAULT_SIGBUS;
 
-	/* If we don't want any read-ahead, don't bother */
-	if (VM_RandomReadHint(vma))
-		goto no_cached_page;
-
 	/*
 	 * Do we have something in the page cache already?
 	 */
-retry_find:
-	page = find_lock_page(mapping, vmf->pgoff);
-	/*
-	 * For sequential accesses, we use the generic readahead logic.
-	 */
-	if (VM_SequentialReadHint(vma)) {
-		if (!page) {
-			page_cache_sync_readahead(mapping, ra, file,
-							   vmf->pgoff, 1);
-			page = find_lock_page(mapping, vmf->pgoff);
-			if (!page)
-				goto no_cached_page;
-		}
-		if (PageReadahead(page)) {
-			page_cache_async_readahead(mapping, ra, file, page,
-							   vmf->pgoff, 1);
-		}
-	}
-
-	if (!page) {
-		unsigned long ra_pages;
-
-		ra->mmap_miss++;
-
+	page = find_get_page(mapping, offset);
+	if (likely(page)) {
 		/*
-		 * Do we miss much more than hit in this file? If so,
-		 * stop bothering with read-ahead. It will only hurt.
+		 * We found the page, so try async readahead before
+		 * waiting for the lock.
 		 */
-		if (ra->mmap_miss > MMAP_LOTSAMISS)
-			goto no_cached_page;
+		do_async_mmap_readahead(vma, ra, file, page, offset);
+		lock_page(page);
 
-		/*
-		 * To keep the pgmajfault counter straight, we need to
-		 * check did_readaround, as this is an inner loop.
-		 */
-		if (!did_readaround) {
-			ret = VM_FAULT_MAJOR;
-			count_vm_event(PGMAJFAULT);
-		}
-		did_readaround = 1;
-		ra_pages = max_sane_readahead(file->f_ra.ra_pages);
-		if (ra_pages) {
-			pgoff_t start = 0;
-
-			if (vmf->pgoff > ra_pages / 2)
-				start = vmf->pgoff - ra_pages / 2;
-			do_page_cache_readahead(mapping, file, start, ra_pages);
+		/* Did it get truncated? */
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			put_page(page);
+			goto no_cached_page;
 		}
-		page = find_lock_page(mapping, vmf->pgoff);
+	} else {
+		/* No page in the page cache at all */
+		do_sync_mmap_readahead(vma, ra, file, offset);
+		count_vm_event(PGMAJFAULT);
+		ret = VM_FAULT_MAJOR;
+retry_find:
+		page = find_lock_page(mapping, offset);
 		if (!page)
 			goto no_cached_page;
 	}
 
-	if (!did_readaround)
-		ra->mmap_miss--;
-
 	/*
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
@@ -1555,18 +1584,18 @@ retry_find:
 	if (unlikely(!PageUptodate(page)))
 		goto page_not_uptodate;
 
-	/* Must recheck i_size under page lock */
+	/*
+	 * Found the page and have a reference on it.
+	 * We must recheck i_size under page lock.
+	 */
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (unlikely(vmf->pgoff >= size)) {
+	if (unlikely(offset >= size)) {
 		unlock_page(page);
 		page_cache_release(page);
 		return VM_FAULT_SIGBUS;
 	}
 
-	/*
-	 * Found the page and have a reference on it.
-	 */
-	ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT;
 	vmf->page = page;
 	return ret | VM_FAULT_LOCKED;
 
@@ -1575,7 +1604,7 @@ no_cached_page:
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, vmf->pgoff);
+	error = page_cache_read(file, offset);
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1595,12 +1624,6 @@ no_cached_page:
 	return VM_FAULT_SIGBUS;
 
 page_not_uptodate:
-	/* IO error path */
-	if (!did_readaround) {
-		ret = VM_FAULT_MAJOR;
-		count_vm_event(PGMAJFAULT);
-	}
-
 	/*
 	 * Umm, take care of errors if the page isn't up-to-date.
 	 * Try to re-read it _once_. We do this synchronously,
@@ -2249,6 +2272,7 @@ again:
 		pagefault_enable();
 		flush_dcache_page(page);
 
+		mark_page_accessed(page);
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
 						page, fsdata);
 		if (unlikely(status < 0))
diff --git a/mm/highmem.c b/mm/highmem.c
index 68eb1d9b63fa..25878cc49daa 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
-#include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
 /*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e83ad2c9228c..cafdcee154e8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -578,41 +578,6 @@ static void free_huge_page(struct page *page)
 		hugetlb_put_quota(mapping, 1);
 }
 
-/*
- * Increment or decrement surplus_huge_pages.  Keep node-specific counters
- * balanced by operating on them in a round-robin fashion.
- * Returns 1 if an adjustment was made.
- */
-static int adjust_pool_surplus(struct hstate *h, int delta)
-{
-	static int prev_nid;
-	int nid = prev_nid;
-	int ret = 0;
-
-	VM_BUG_ON(delta != -1 && delta != 1);
-	do {
-		nid = next_node(nid, node_online_map);
-		if (nid == MAX_NUMNODES)
-			nid = first_node(node_online_map);
-
-		/* To shrink on this node, there must be a surplus page */
-		if (delta < 0 && !h->surplus_huge_pages_node[nid])
-			continue;
-		/* Surplus cannot exceed the total number of pages */
-		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
-						h->nr_huge_pages_node[nid])
-			continue;
-
-		h->surplus_huge_pages += delta;
-		h->surplus_huge_pages_node[nid] += delta;
-		ret = 1;
-		break;
-	} while (nid != prev_nid);
-
-	prev_nid = nid;
-	return ret;
-}
-
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	set_compound_page_dtor(page, free_huge_page);
@@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	put_page(page); /* free it into the hugepage allocator */
 }
 
+static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+	int i;
+	int nr_pages = 1 << order;
+	struct page *p = page + 1;
+
+	/* we rely on prep_new_huge_page to set the destructor */
+	set_compound_order(page, order);
+	__SetPageHead(page);
+	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+		__SetPageTail(p);
+		p->first_page = page;
+	}
+}
+
+int PageHuge(struct page *page)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageCompound(page))
+		return 0;
+
+	page = compound_head(page);
+	dtor = get_compound_page_dtor(page);
+
+	return dtor == free_huge_page;
+}
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
@@ -630,7 +623,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 	if (h->order >= MAX_ORDER)
 		return NULL;
 
-	page = alloc_pages_node(nid,
+	page = alloc_pages_exact_node(nid,
 		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
 		huge_page_order(h));
@@ -649,7 +642,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
  * Use a helper variable to find the next node and then
  * copy it back to hugetlb_next_nid afterwards:
  * otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
  * But we don't need to use a spin_lock here: it really
  * doesn't matter if occasionally a racer chooses the
  * same nid as we do.  Move nid forward in the mask even
@@ -875,7 +868,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * can no longer free unreserved surplus pages. This occurs when
 	 * the nodes with surplus pages have no free pages.
 	 */
-	unsigned long remaining_iterations = num_online_nodes();
+	unsigned long remaining_iterations = nr_online_nodes;
 
 	/* Uncommit the reservation */
 	h->resv_huge_pages -= unused_resv_pages;
@@ -904,7 +897,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 			h->surplus_huge_pages--;
 			h->surplus_huge_pages_node[nid]--;
 			nr_pages--;
-			remaining_iterations = num_online_nodes();
+			remaining_iterations = nr_online_nodes;
 		}
 	}
 }
@@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count)
 }
 #endif
 
+/*
+ * Increment or decrement surplus_huge_pages.  Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(struct hstate *h, int delta)
+{
+	static int prev_nid;
+	int nid = prev_nid;
+	int ret = 0;
+
+	VM_BUG_ON(delta != -1 && delta != 1);
+	do {
+		nid = next_node(nid, node_online_map);
+		if (nid == MAX_NUMNODES)
+			nid = first_node(node_online_map);
+
+		/* To shrink on this node, there must be a surplus page */
+		if (delta < 0 && !h->surplus_huge_pages_node[nid])
+			continue;
+		/* Surplus cannot exceed the total number of pages */
+		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+						h->nr_huge_pages_node[nid])
+			continue;
+
+		h->surplus_huge_pages += delta;
+		h->surplus_huge_pages_node[nid] += delta;
+		ret = 1;
+		break;
+	} while (nid != prev_nid);
+
+	prev_nid = nid;
+	return ret;
+}
+
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
 static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {
@@ -1957,7 +1985,7 @@ static struct page *hugetlbfs_pagecache_page(struct hstate *h,
 }
 
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long address, pte_t *ptep, int write_access)
+			unsigned long address, pte_t *ptep, unsigned int flags)
 {
 	struct hstate *h = hstate_vma(vma);
 	int ret = VM_FAULT_SIGBUS;
@@ -2025,7 +2053,7 @@ retry:
 	 * any allocations necessary to record that reservation occur outside
 	 * the spinlock.
 	 */
-	if (write_access && !(vma->vm_flags & VM_SHARED))
+	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
 		if (vma_needs_reservation(h, vma, address) < 0) {
 			ret = VM_FAULT_OOM;
 			goto backout_unlocked;
@@ -2044,7 +2072,7 @@ retry:
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
 
-	if (write_access && !(vma->vm_flags & VM_SHARED)) {
+	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
 		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
 	}
@@ -2063,7 +2091,7 @@ backout_unlocked:
 }
 
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long address, int write_access)
+			unsigned long address, unsigned int flags)
 {
 	pte_t *ptep;
 	pte_t entry;
@@ -2084,7 +2112,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	mutex_lock(&hugetlb_instantiation_mutex);
 	entry = huge_ptep_get(ptep);
 	if (huge_pte_none(entry)) {
-		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
+		ret = hugetlb_no_page(mm, vma, address, ptep, flags);
 		goto out_mutex;
 	}
 
@@ -2098,7 +2126,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * page now as it is used to determine if a reservation has been
 	 * consumed.
 	 */
-	if (write_access && !pte_write(entry)) {
+	if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) {
 		if (vma_needs_reservation(h, vma, address) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
@@ -2115,7 +2143,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_page_table_lock;
 
 
-	if (write_access) {
+	if (flags & FAULT_FLAG_WRITE) {
 		if (!pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
 							pagecache_page);
@@ -2124,7 +2152,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
-	if (huge_ptep_set_access_flags(vma, address, ptep, entry, write_access))
+	if (huge_ptep_set_access_flags(vma, address, ptep, entry,
+						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, entry);
 
 out_page_table_lock:
@@ -2341,7 +2370,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
 	spin_lock(&inode->i_lock);
-	inode->i_blocks -= blocks_per_huge_page(h);
+	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
 
 	hugetlb_put_quota(inode->i_mapping, (chg - freed));
diff --git a/mm/init-mm.c b/mm/init-mm.c
new file mode 100644
index 000000000000..57aba0da9668
--- /dev/null
+++ b/mm/init-mm.c
@@ -0,0 +1,20 @@
+#include <linux/mm_types.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
+
+#include <asm/atomic.h>
+#include <asm/pgtable.h>
+
+struct mm_struct init_mm = {
+	.mm_rb		= RB_ROOT,
+	.pgd		= swapper_pg_dir,
+	.mm_users	= ATOMIC_INIT(2),
+	.mm_count	= ATOMIC_INIT(1),
+	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
+	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+	.cpu_vm_mask	= CPU_MASK_ALL,
+};
diff --git a/mm/internal.h b/mm/internal.h
index 987bb03fbdd8..f290c4db528b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -16,9 +16,6 @@
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
-extern void prep_compound_page(struct page *page, unsigned long order);
-extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
-
 static inline void set_page_count(struct page *page, int v)
 {
 	atomic_set(&page->_count, v);
@@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page);
  */
 extern unsigned long highest_memmap_pfn;
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void prep_compound_page(struct page *page, unsigned long order);
+
 
 /*
  * function for dealing with page's order in buddy system.
@@ -74,7 +73,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
 }
 #endif
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * unevictable_migrate_page() called only from migrate_page_copy() to
  * migrate unevictable flag to new page.
@@ -86,11 +84,6 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old)
 	if (TestClearPageUnevictable(old))
 		SetPageUnevictable(new);
 }
-#else
-static inline void unevictable_migrate_page(struct page *new, struct page *old)
-{
-}
-#endif
 
 #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
 /*
@@ -150,23 +143,6 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 	}
 }
 
-/*
- * free_page_mlock() -- clean up attempts to free and mlocked() page.
- * Page should not be on lru, so no need to fix that up.
- * free_pages_check() will verify...
- */
-static inline void free_page_mlock(struct page *page)
-{
-	if (unlikely(TestClearPageMlocked(page))) {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		__dec_zone_page_state(page, NR_MLOCK);
-		__count_vm_event(UNEVICTABLE_MLOCKFREED);
-		local_irq_restore(flags);
-	}
-}
-
 #else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 {
@@ -175,7 +151,6 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 static inline void clear_page_mlock(struct page *page) { }
 static inline void mlock_vma_page(struct page *page) { }
 static inline void mlock_migrate_page(struct page *new, struct page *old) { }
-static inline void free_page_mlock(struct page *page) { }
 
 #endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 
@@ -284,4 +259,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int len, int flags,
 		     struct page **pages, struct vm_area_struct **vmas);
 
+#define ZONE_RECLAIM_NOSCAN	-2
+#define ZONE_RECLAIM_FULL	-1
+#define ZONE_RECLAIM_SOME	0
+#define ZONE_RECLAIM_SUCCESS	1
 #endif
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
new file mode 100644
index 000000000000..fd814fd61319
--- /dev/null
+++ b/mm/kmemcheck.c
@@ -0,0 +1,122 @@
+#include <linux/gfp.h>
+#include <linux/mm_types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/kmemcheck.h>
+
+void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	pages = 1 << order;
+
+	/*
+	 * With kmemcheck enabled, we need to allocate a memory area for the
+	 * shadow bits as well.
+	 */
+	shadow = alloc_pages_node(node, flags | __GFP_NOTRACK, order);
+	if (!shadow) {
+		if (printk_ratelimit())
+			printk(KERN_ERR "kmemcheck: failed to allocate "
+				"shadow bitmap\n");
+		return;
+	}
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = page_address(&shadow[i]);
+
+	/*
+	 * Mark it as non-present for the MMU so that our accesses to
+	 * this memory will trigger a page fault and let us analyze
+	 * the memory accesses.
+	 */
+	kmemcheck_hide_pages(page, pages);
+}
+
+void kmemcheck_free_shadow(struct page *page, int order)
+{
+	struct page *shadow;
+	int pages;
+	int i;
+
+	if (!kmemcheck_page_is_tracked(page))
+		return;
+
+	pages = 1 << order;
+
+	kmemcheck_show_pages(page, pages);
+
+	shadow = virt_to_page(page[0].shadow);
+
+	for(i = 0; i < pages; ++i)
+		page[i].shadow = NULL;
+
+	__free_pages(shadow, order);
+}
+
+void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
+			  size_t size)
+{
+	/*
+	 * Has already been memset(), which initializes the shadow for us
+	 * as well.
+	 */
+	if (gfpflags & __GFP_ZERO)
+		return;
+
+	/* No need to initialize the shadow of a non-tracked slab. */
+	if (s->flags & SLAB_NOTRACK)
+		return;
+
+	if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) {
+		/*
+		 * Allow notracked objects to be allocated from
+		 * tracked caches. Note however that these objects
+		 * will still get page faults on access, they just
+		 * won't ever be flagged as uninitialized. If page
+		 * faults are not acceptable, the slab cache itself
+		 * should be marked NOTRACK.
+		 */
+		kmemcheck_mark_initialized(object, size);
+	} else if (!s->ctor) {
+		/*
+		 * New objects should be marked uninitialized before
+		 * they're returned to the called.
+		 */
+		kmemcheck_mark_uninitialized(object, size);
+	}
+}
+
+void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
+{
+	/* TODO: RCU freeing is unsupported for now; hide false positives. */
+	if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
+		kmemcheck_mark_freed(object, size);
+}
+
+void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order,
+			       gfp_t gfpflags)
+{
+	int pages;
+
+	if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK))
+		return;
+
+	pages = 1 << order;
+
+	/*
+	 * NOTE: We choose to track GFP_ZERO pages too; in fact, they
+	 * can become uninitialized by copying uninitialized memory
+	 * into them.
+	 */
+
+	/* XXX: Can use zone->node for node? */
+	kmemcheck_alloc_shadow(page, order, gfpflags, -1);
+
+	if (gfpflags & __GFP_ZERO)
+		kmemcheck_mark_initialized_pages(page, pages);
+	else
+		kmemcheck_mark_uninitialized_pages(page, pages);
+}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 58ec86c9e58a..487267310a84 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -48,10 +48,10 @@
  *   scanned. This list is only modified during a scanning episode when the
  *   scan_mutex is held. At the end of a scan, the gray_list is always empty.
  *   Note that the kmemleak_object.use_count is incremented when an object is
- *   added to the gray_list and therefore cannot be freed
- * - kmemleak_mutex (mutex): prevents multiple users of the "kmemleak" debugfs
- *   file together with modifications to the memory scanning parameters
- *   including the scan_thread pointer
+ *   added to the gray_list and therefore cannot be freed. This mutex also
+ *   prevents multiple users of the "kmemleak" debugfs file together with
+ *   modifications to the memory scanning parameters including the scan_thread
+ *   pointer
  *
  * The kmemleak_object structures have a use_count incremented or decremented
  * using the get_object()/put_object() functions. When the use_count becomes
@@ -61,6 +61,8 @@
  * structure.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -101,14 +103,16 @@
  * Kmemleak configuration and common defines.
  */
 #define MAX_TRACE		16	/* stack trace length */
-#define REPORTS_NR		50	/* maximum number of reported leaks */
 #define MSECS_MIN_AGE		5000	/* minimum object age for reporting */
-#define MSECS_SCAN_YIELD	10	/* CPU yielding period */
 #define SECS_FIRST_SCAN		60	/* delay before the first scan */
 #define SECS_SCAN_WAIT		600	/* subsequent auto scanning delay */
+#define GRAY_LIST_PASSES	25	/* maximum number of gray list scans */
 
 #define BYTES_PER_POINTER	sizeof(void *)
 
+/* GFP bitmask for kmemleak internal allocations */
+#define GFP_KMEMLEAK_MASK	(GFP_KERNEL | GFP_ATOMIC)
+
 /* scanning area inside a memory block */
 struct kmemleak_scan_area {
 	struct hlist_node node;
@@ -154,6 +158,8 @@ struct kmemleak_object {
 #define OBJECT_REPORTED		(1 << 1)
 /* flag set to not scan the object */
 #define OBJECT_NO_SCAN		(1 << 2)
+/* flag set on newly allocated objects */
+#define OBJECT_NEW		(1 << 3)
 
 /* the list of all allocated objects */
 static LIST_HEAD(object_list);
@@ -181,27 +187,21 @@ static atomic_t kmemleak_error = ATOMIC_INIT(0);
 static unsigned long min_addr = ULONG_MAX;
 static unsigned long max_addr;
 
-/* used for yielding the CPU to other tasks during scanning */
-static unsigned long next_scan_yield;
 static struct task_struct *scan_thread;
-static unsigned long jiffies_scan_yield;
+/* used to avoid reporting of recently allocated objects */
 static unsigned long jiffies_min_age;
+static unsigned long jiffies_last_scan;
 /* delay between automatic memory scannings */
 static signed long jiffies_scan_wait;
 /* enables or disables the task stacks scanning */
-static int kmemleak_stack_scan;
-/* mutex protecting the memory scanning */
+static int kmemleak_stack_scan = 1;
+/* protects the memory scanning, parameters and debug/kmemleak file access */
 static DEFINE_MUTEX(scan_mutex);
-/* mutex protecting the access to the /sys/kernel/debug/kmemleak file */
-static DEFINE_MUTEX(kmemleak_mutex);
-
-/* number of leaks reported (for limitation purposes) */
-static int reported_leaks;
 
 /*
- * Early object allocation/freeing logging. Kkmemleak is initialized after the
+ * Early object allocation/freeing logging. Kmemleak is initialized after the
  * kernel allocator. However, both the kernel allocator and kmemleak may
- * allocate memory blocks which need to be tracked. Kkmemleak defines an
+ * allocate memory blocks which need to be tracked. Kmemleak defines an
  * arbitrary buffer to hold the allocation/freeing information before it is
  * fully initialized.
  */
@@ -210,6 +210,7 @@ static int reported_leaks;
 enum {
 	KMEMLEAK_ALLOC,
 	KMEMLEAK_FREE,
+	KMEMLEAK_FREE_PART,
 	KMEMLEAK_NOT_LEAK,
 	KMEMLEAK_IGNORE,
 	KMEMLEAK_SCAN_AREA,
@@ -230,7 +231,7 @@ struct early_log {
 };
 
 /* early logging buffer and current position */
-static struct early_log early_log[200];
+static struct early_log early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE];
 static int crt_early_log;
 
 static void kmemleak_disable(void);
@@ -245,10 +246,10 @@ static void kmemleak_disable(void);
 
 /*
  * Macro invoked when a serious kmemleak condition occured and cannot be
- * recovered from. Kkmemleak will be disabled and further allocation/freeing
+ * recovered from. Kmemleak will be disabled and further allocation/freeing
  * tracing no longer available.
  */
-#define kmemleak_panic(x...)	do {	\
+#define kmemleak_stop(x...)	do {	\
 	kmemleak_warn(x);		\
 	kmemleak_disable();		\
 } while (0)
@@ -273,13 +274,9 @@ static int color_gray(const struct kmemleak_object *object)
 	return object->min_count != -1 && object->count >= object->min_count;
 }
 
-/*
- * Objects are considered referenced if their color is gray and they have not
- * been deleted.
- */
-static int referenced_object(struct kmemleak_object *object)
+static int color_black(const struct kmemleak_object *object)
 {
-	return (object->flags & OBJECT_ALLOCATED) && color_gray(object);
+	return object->min_count == -1;
 }
 
 /*
@@ -290,42 +287,28 @@ static int referenced_object(struct kmemleak_object *object)
 static int unreferenced_object(struct kmemleak_object *object)
 {
 	return (object->flags & OBJECT_ALLOCATED) && color_white(object) &&
-		time_is_before_eq_jiffies(object->jiffies + jiffies_min_age);
+		time_before_eq(object->jiffies + jiffies_min_age,
+			       jiffies_last_scan);
 }
 
 /*
- * Printing of the (un)referenced objects information, either to the seq file
- * or to the kernel log. The print_referenced/print_unreferenced functions
- * must be called with the object->lock held.
+ * Printing of the unreferenced objects information to the seq file. The
+ * print_unreferenced function must be called with the object->lock held.
  */
-#define print_helper(seq, x...)	do {	\
-	struct seq_file *s = (seq);	\
-	if (s)				\
-		seq_printf(s, x);	\
-	else				\
-		pr_info(x);		\
-} while (0)
-
-static void print_referenced(struct kmemleak_object *object)
-{
-	pr_info("kmemleak: referenced object 0x%08lx (size %zu)\n",
-		object->pointer, object->size);
-}
-
 static void print_unreferenced(struct seq_file *seq,
 			       struct kmemleak_object *object)
 {
 	int i;
 
-	print_helper(seq, "kmemleak: unreferenced object 0x%08lx (size %zu):\n",
-		     object->pointer, object->size);
-	print_helper(seq, "  comm \"%s\", pid %d, jiffies %lu\n",
-		     object->comm, object->pid, object->jiffies);
-	print_helper(seq, "  backtrace:\n");
+	seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n",
+		   object->pointer, object->size);
+	seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu\n",
+		   object->comm, object->pid, object->jiffies);
+	seq_printf(seq, "  backtrace:\n");
 
 	for (i = 0; i < object->trace_len; i++) {
 		void *ptr = (void *)object->trace[i];
-		print_helper(seq, "    [<%p>] %pS\n", ptr, ptr);
+		seq_printf(seq, "    [<%p>] %pS\n", ptr, ptr);
 	}
 }
 
@@ -341,7 +324,7 @@ static void dump_object_info(struct kmemleak_object *object)
 	trace.nr_entries = object->trace_len;
 	trace.entries = object->trace;
 
-	pr_notice("kmemleak: Object 0x%08lx (size %zu):\n",
+	pr_notice("Object 0x%08lx (size %zu):\n",
 		  object->tree_node.start, object->size);
 	pr_notice("  comm \"%s\", pid %d, jiffies %lu\n",
 		  object->comm, object->pid, object->jiffies);
@@ -369,7 +352,7 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
 		object = prio_tree_entry(node, struct kmemleak_object,
 					 tree_node);
 		if (!alias && object->pointer != ptr) {
-			kmemleak_warn("kmemleak: Found object by alias");
+			kmemleak_warn("Found object by alias");
 			object = NULL;
 		}
 	} else
@@ -462,10 +445,9 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
 	struct prio_tree_node *node;
 	struct stack_trace trace;
 
-	object = kmem_cache_alloc(object_cache, gfp & ~GFP_SLAB_BUG_MASK);
+	object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK);
 	if (!object) {
-		kmemleak_panic("kmemleak: Cannot allocate a kmemleak_object "
-			       "structure\n");
+		kmemleak_stop("Cannot allocate a kmemleak_object structure\n");
 		return;
 	}
 
@@ -474,7 +456,7 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
 	INIT_HLIST_HEAD(&object->area_list);
 	spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
-	object->flags = OBJECT_ALLOCATED;
+	object->flags = OBJECT_ALLOCATED | OBJECT_NEW;
 	object->pointer = ptr;
 	object->size = size;
 	object->min_count = min_count;
@@ -524,8 +506,8 @@ static void create_object(unsigned long ptr, size_t size, int min_count,
 	if (node != &object->tree_node) {
 		unsigned long flags;
 
-		kmemleak_panic("kmemleak: Cannot insert 0x%lx into the object "
-			       "search tree (already existing)\n", ptr);
+		kmemleak_stop("Cannot insert 0x%lx into the object search tree "
+			      "(already existing)\n", ptr);
 		object = lookup_object(ptr, 1);
 		spin_lock_irqsave(&object->lock, flags);
 		dump_object_info(object);
@@ -542,39 +524,87 @@ out:
  * Remove the metadata (struct kmemleak_object) for a memory block from the
  * object_list and object_tree_root and decrement its use_count.
  */
-static void delete_object(unsigned long ptr)
+static void __delete_object(struct kmemleak_object *object)
 {
 	unsigned long flags;
-	struct kmemleak_object *object;
 
 	write_lock_irqsave(&kmemleak_lock, flags);
-	object = lookup_object(ptr, 0);
-	if (!object) {
-		kmemleak_warn("kmemleak: Freeing unknown object at 0x%08lx\n",
-			      ptr);
-		write_unlock_irqrestore(&kmemleak_lock, flags);
-		return;
-	}
 	prio_tree_remove(&object_tree_root, &object->tree_node);
 	list_del_rcu(&object->object_list);
 	write_unlock_irqrestore(&kmemleak_lock, flags);
 
 	WARN_ON(!(object->flags & OBJECT_ALLOCATED));
-	WARN_ON(atomic_read(&object->use_count) < 1);
+	WARN_ON(atomic_read(&object->use_count) < 2);
 
 	/*
 	 * Locking here also ensures that the corresponding memory block
 	 * cannot be freed when it is being scanned.
 	 */
 	spin_lock_irqsave(&object->lock, flags);
-	if (object->flags & OBJECT_REPORTED)
-		print_referenced(object);
 	object->flags &= ~OBJECT_ALLOCATED;
 	spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 
 /*
+ * Look up the metadata (struct kmemleak_object) corresponding to ptr and
+ * delete it.
+ */
+static void delete_object_full(unsigned long ptr)
+{
+	struct kmemleak_object *object;
+
+	object = find_and_get_object(ptr, 0);
+	if (!object) {
+#ifdef DEBUG
+		kmemleak_warn("Freeing unknown object at 0x%08lx\n",
+			      ptr);
+#endif
+		return;
+	}
+	__delete_object(object);
+	put_object(object);
+}
+
+/*
+ * Look up the metadata (struct kmemleak_object) corresponding to ptr and
+ * delete it. If the memory block is partially freed, the function may create
+ * additional metadata for the remaining parts of the block.
+ */
+static void delete_object_part(unsigned long ptr, size_t size)
+{
+	struct kmemleak_object *object;
+	unsigned long start, end;
+
+	object = find_and_get_object(ptr, 1);
+	if (!object) {
+#ifdef DEBUG
+		kmemleak_warn("Partially freeing unknown object at 0x%08lx "
+			      "(size %zu)\n", ptr, size);
+#endif
+		return;
+	}
+	__delete_object(object);
+
+	/*
+	 * Create one or two objects that may result from the memory block
+	 * split. Note that partial freeing is only done by free_bootmem() and
+	 * this happens before kmemleak_init() is called. The path below is
+	 * only executed during early log recording in kmemleak_init(), so
+	 * GFP_KERNEL is enough.
+	 */
+	start = object->pointer;
+	end = object->pointer + object->size;
+	if (ptr > start)
+		create_object(start, ptr - start, object->min_count,
+			      GFP_KERNEL);
+	if (ptr + size < end)
+		create_object(ptr + size, end - ptr - size, object->min_count,
+			      GFP_KERNEL);
+
+	put_object(object);
+}
+/*
  * Make a object permanently as gray-colored so that it can no longer be
  * reported as a leak. This is used in general to mark a false positive.
  */
@@ -585,8 +615,7 @@ static void make_gray_object(unsigned long ptr)
 
 	object = find_and_get_object(ptr, 0);
 	if (!object) {
-		kmemleak_warn("kmemleak: Graying unknown object at 0x%08lx\n",
-			      ptr);
+		kmemleak_warn("Graying unknown object at 0x%08lx\n", ptr);
 		return;
 	}
 
@@ -607,8 +636,7 @@ static void make_black_object(unsigned long ptr)
 
 	object = find_and_get_object(ptr, 0);
 	if (!object) {
-		kmemleak_warn("kmemleak: Blacking unknown object at 0x%08lx\n",
-			      ptr);
+		kmemleak_warn("Blacking unknown object at 0x%08lx\n", ptr);
 		return;
 	}
 
@@ -631,21 +659,20 @@ static void add_scan_area(unsigned long ptr, unsigned long offset,
 
 	object = find_and_get_object(ptr, 0);
 	if (!object) {
-		kmemleak_warn("kmemleak: Adding scan area to unknown "
-			      "object at 0x%08lx\n", ptr);
+		kmemleak_warn("Adding scan area to unknown object at 0x%08lx\n",
+			      ptr);
 		return;
 	}
 
-	area = kmem_cache_alloc(scan_area_cache, gfp & ~GFP_SLAB_BUG_MASK);
+	area = kmem_cache_alloc(scan_area_cache, gfp & GFP_KMEMLEAK_MASK);
 	if (!area) {
-		kmemleak_warn("kmemleak: Cannot allocate a scan area\n");
+		kmemleak_warn("Cannot allocate a scan area\n");
 		goto out;
 	}
 
 	spin_lock_irqsave(&object->lock, flags);
 	if (offset + length > object->size) {
-		kmemleak_warn("kmemleak: Scan area larger than object "
-			      "0x%08lx\n", ptr);
+		kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
 		dump_object_info(object);
 		kmem_cache_free(scan_area_cache, area);
 		goto out_unlock;
@@ -674,8 +701,7 @@ static void object_no_scan(unsigned long ptr)
 
 	object = find_and_get_object(ptr, 0);
 	if (!object) {
-		kmemleak_warn("kmemleak: Not scanning unknown object at "
-			      "0x%08lx\n", ptr);
+		kmemleak_warn("Not scanning unknown object at 0x%08lx\n", ptr);
 		return;
 	}
 
@@ -696,7 +722,8 @@ static void log_early(int op_type, const void *ptr, size_t size,
 	struct early_log *log;
 
 	if (crt_early_log >= ARRAY_SIZE(early_log)) {
-		kmemleak_panic("kmemleak: Early log buffer exceeded\n");
+		pr_warning("Early log buffer exceeded\n");
+		kmemleak_disable();
 		return;
 	}
 
@@ -741,13 +768,28 @@ void kmemleak_free(const void *ptr)
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
 	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
-		delete_object((unsigned long)ptr);
+		delete_object_full((unsigned long)ptr);
 	else if (atomic_read(&kmemleak_early_log))
 		log_early(KMEMLEAK_FREE, ptr, 0, 0, 0, 0);
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
 
 /*
+ * Partial memory freeing function callback. This function is usually called
+ * from bootmem allocator when (part of) a memory block is freed.
+ */
+void kmemleak_free_part(const void *ptr, size_t size)
+{
+	pr_debug("%s(0x%p)\n", __func__, ptr);
+
+	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+		delete_object_part((unsigned long)ptr, size);
+	else if (atomic_read(&kmemleak_early_log))
+		log_early(KMEMLEAK_FREE_PART, ptr, size, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(kmemleak_free_part);
+
+/*
  * Mark an already allocated memory block as a false positive. This will cause
  * the block to no longer be reported as leak and always be scanned.
  */
@@ -808,21 +850,6 @@ void kmemleak_no_scan(const void *ptr)
 EXPORT_SYMBOL(kmemleak_no_scan);
 
 /*
- * Yield the CPU so that other tasks get a chance to run.  The yielding is
- * rate-limited to avoid excessive number of calls to the schedule() function
- * during memory scanning.
- */
-static void scan_yield(void)
-{
-	might_sleep();
-
-	if (time_is_before_eq_jiffies(next_scan_yield)) {
-		schedule();
-		next_scan_yield = jiffies + jiffies_scan_yield;
-	}
-}
-
-/*
  * Memory scanning is a long process and it needs to be interruptable. This
  * function checks whether such interrupt condition occured.
  */
@@ -848,7 +875,7 @@ static int scan_should_stop(void)
  * found to the gray list.
  */
 static void scan_block(void *_start, void *_end,
-		       struct kmemleak_object *scanned)
+		       struct kmemleak_object *scanned, int allow_resched)
 {
 	unsigned long *ptr;
 	unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER);
@@ -859,18 +886,11 @@ static void scan_block(void *_start, void *_end,
 		unsigned long pointer = *ptr;
 		struct kmemleak_object *object;
 
+		if (allow_resched)
+			cond_resched();
 		if (scan_should_stop())
 			break;
 
-		/*
-		 * When scanning a memory block with a corresponding
-		 * kmemleak_object, the CPU yielding is handled in the calling
-		 * code since it holds the object->lock to avoid the block
-		 * freeing.
-		 */
-		if (!scanned)
-			scan_yield();
-
 		object = find_and_get_object(pointer, 1);
 		if (!object)
 			continue;
@@ -931,12 +951,12 @@ static void scan_object(struct kmemleak_object *object)
 		goto out;
 	if (hlist_empty(&object->area_list))
 		scan_block((void *)object->pointer,
-			   (void *)(object->pointer + object->size), object);
+			   (void *)(object->pointer + object->size), object, 0);
 	else
 		hlist_for_each_entry(area, elem, &object->area_list, node)
 			scan_block((void *)(object->pointer + area->offset),
 				   (void *)(object->pointer + area->offset
-					    + area->length), object);
+					    + area->length), object, 0);
 out:
 	spin_unlock_irqrestore(&object->lock, flags);
 }
@@ -952,6 +972,10 @@ static void kmemleak_scan(void)
 	struct kmemleak_object *object, *tmp;
 	struct task_struct *task;
 	int i;
+	int new_leaks = 0;
+	int gray_list_pass = 0;
+
+	jiffies_last_scan = jiffies;
 
 	/* prepare the kmemleak_object's */
 	rcu_read_lock();
@@ -963,13 +987,14 @@ static void kmemleak_scan(void)
 		 * 1 reference to any object at this point.
 		 */
 		if (atomic_read(&object->use_count) > 1) {
-			pr_debug("kmemleak: object->use_count = %d\n",
+			pr_debug("object->use_count = %d\n",
 				 atomic_read(&object->use_count));
 			dump_object_info(object);
 		}
 #endif
 		/* reset the reference count (whiten the object) */
 		object->count = 0;
+		object->flags &= ~OBJECT_NEW;
 		if (color_gray(object) && get_object(object))
 			list_add_tail(&object->gray_list, &gray_list);
 
@@ -978,14 +1003,14 @@ static void kmemleak_scan(void)
 	rcu_read_unlock();
 
 	/* data/bss scanning */
-	scan_block(_sdata, _edata, NULL);
-	scan_block(__bss_start, __bss_stop, NULL);
+	scan_block(_sdata, _edata, NULL, 1);
+	scan_block(__bss_start, __bss_stop, NULL, 1);
 
 #ifdef CONFIG_SMP
 	/* per-cpu sections scanning */
 	for_each_possible_cpu(i)
 		scan_block(__per_cpu_start + per_cpu_offset(i),
-			   __per_cpu_end + per_cpu_offset(i), NULL);
+			   __per_cpu_end + per_cpu_offset(i), NULL, 1);
 #endif
 
 	/*
@@ -1007,7 +1032,7 @@ static void kmemleak_scan(void)
 			/* only scan if page is in use */
 			if (page_count(page) == 0)
 				continue;
-			scan_block(page, page + 1, NULL);
+			scan_block(page, page + 1, NULL, 1);
 		}
 	}
 
@@ -1019,7 +1044,8 @@ static void kmemleak_scan(void)
 		read_lock(&tasklist_lock);
 		for_each_process(task)
 			scan_block(task_stack_page(task),
-				   task_stack_page(task) + THREAD_SIZE, NULL);
+				   task_stack_page(task) + THREAD_SIZE,
+				   NULL, 0);
 		read_unlock(&tasklist_lock);
 	}
 
@@ -1031,9 +1057,10 @@ static void kmemleak_scan(void)
 	 * kmemleak objects cannot be freed from outside the loop because their
 	 * use_count was increased.
 	 */
+repeat:
 	object = list_entry(gray_list.next, typeof(*object), gray_list);
 	while (&object->gray_list != &gray_list) {
-		scan_yield();
+		cond_resched();
 
 		/* may add new objects to the list */
 		if (!scan_should_stop())
@@ -1048,7 +1075,59 @@ static void kmemleak_scan(void)
 
 		object = tmp;
 	}
+
+	if (scan_should_stop() || ++gray_list_pass >= GRAY_LIST_PASSES)
+		goto scan_end;
+
+	/*
+	 * Check for new objects allocated during this scanning and add them
+	 * to the gray list.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(object, &object_list, object_list) {
+		spin_lock_irqsave(&object->lock, flags);
+		if ((object->flags & OBJECT_NEW) && !color_black(object) &&
+		    get_object(object)) {
+			object->flags &= ~OBJECT_NEW;
+			list_add_tail(&object->gray_list, &gray_list);
+		}
+		spin_unlock_irqrestore(&object->lock, flags);
+	}
+	rcu_read_unlock();
+
+	if (!list_empty(&gray_list))
+		goto repeat;
+
+scan_end:
 	WARN_ON(!list_empty(&gray_list));
+
+	/*
+	 * If scanning was stopped or new objects were being allocated at a
+	 * higher rate than gray list scanning, do not report any new
+	 * unreferenced objects.
+	 */
+	if (scan_should_stop() || gray_list_pass >= GRAY_LIST_PASSES)
+		return;
+
+	/*
+	 * Scanning result reporting.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(object, &object_list, object_list) {
+		spin_lock_irqsave(&object->lock, flags);
+		if (unreferenced_object(object) &&
+		    !(object->flags & OBJECT_REPORTED)) {
+			object->flags |= OBJECT_REPORTED;
+			new_leaks++;
+		}
+		spin_unlock_irqrestore(&object->lock, flags);
+	}
+	rcu_read_unlock();
+
+	if (new_leaks)
+		pr_info("%d new suspected memory leaks (see "
+			"/sys/kernel/debug/kmemleak)\n", new_leaks);
+
 }
 
 /*
@@ -1059,7 +1138,8 @@ static int kmemleak_scan_thread(void *arg)
 {
 	static int first_run = 1;
 
-	pr_info("kmemleak: Automatic memory scanning thread started\n");
+	pr_info("Automatic memory scanning thread started\n");
+	set_user_nice(current, 10);
 
 	/*
 	 * Wait before the first scan to allow the system to fully initialize.
@@ -1070,49 +1150,25 @@ static int kmemleak_scan_thread(void *arg)
 	}
 
 	while (!kthread_should_stop()) {
-		struct kmemleak_object *object;
 		signed long timeout = jiffies_scan_wait;
 
 		mutex_lock(&scan_mutex);
-
 		kmemleak_scan();
-		reported_leaks = 0;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu(object, &object_list, object_list) {
-			unsigned long flags;
-
-			if (reported_leaks >= REPORTS_NR)
-				break;
-			spin_lock_irqsave(&object->lock, flags);
-			if (!(object->flags & OBJECT_REPORTED) &&
-			    unreferenced_object(object)) {
-				print_unreferenced(NULL, object);
-				object->flags |= OBJECT_REPORTED;
-				reported_leaks++;
-			} else if ((object->flags & OBJECT_REPORTED) &&
-				   referenced_object(object)) {
-				print_referenced(object);
-				object->flags &= ~OBJECT_REPORTED;
-			}
-			spin_unlock_irqrestore(&object->lock, flags);
-		}
-		rcu_read_unlock();
-
 		mutex_unlock(&scan_mutex);
+
 		/* wait before the next scan */
 		while (timeout && !kthread_should_stop())
 			timeout = schedule_timeout_interruptible(timeout);
 	}
 
-	pr_info("kmemleak: Automatic memory scanning thread ended\n");
+	pr_info("Automatic memory scanning thread ended\n");
 
 	return 0;
 }
 
 /*
  * Start the automatic memory scanning thread. This function must be called
- * with the kmemleak_mutex held.
+ * with the scan_mutex held.
  */
 void start_scan_thread(void)
 {
@@ -1120,14 +1176,14 @@ void start_scan_thread(void)
 		return;
 	scan_thread = kthread_run(kmemleak_scan_thread, NULL, "kmemleak");
 	if (IS_ERR(scan_thread)) {
-		pr_warning("kmemleak: Failed to create the scan thread\n");
+		pr_warning("Failed to create the scan thread\n");
 		scan_thread = NULL;
 	}
 }
 
 /*
  * Stop the automatic memory scanning thread. This function must be called
- * with the kmemleak_mutex held.
+ * with the scan_mutex held.
  */
 void stop_scan_thread(void)
 {
@@ -1146,13 +1202,11 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct kmemleak_object *object;
 	loff_t n = *pos;
+	int err;
 
-	if (!n) {
-		kmemleak_scan();
-		reported_leaks = 0;
-	}
-	if (reported_leaks >= REPORTS_NR)
-		return NULL;
+	err = mutex_lock_interruptible(&scan_mutex);
+	if (err < 0)
+		return ERR_PTR(err);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
@@ -1163,7 +1217,6 @@ static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
 	}
 	object = NULL;
 out:
-	rcu_read_unlock();
 	return object;
 }
 
@@ -1178,17 +1231,13 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct list_head *n = &prev_obj->object_list;
 
 	++(*pos);
-	if (reported_leaks >= REPORTS_NR)
-		goto out;
 
-	rcu_read_lock();
 	list_for_each_continue_rcu(n, &object_list) {
 		next_obj = list_entry(n, struct kmemleak_object, object_list);
 		if (get_object(next_obj))
 			break;
 	}
-	rcu_read_unlock();
-out:
+
 	put_object(prev_obj);
 	return next_obj;
 }
@@ -1198,8 +1247,16 @@ out:
  */
 static void kmemleak_seq_stop(struct seq_file *seq, void *v)
 {
-	if (v)
-		put_object(v);
+	if (!IS_ERR(v)) {
+		/*
+		 * kmemleak_seq_start may return ERR_PTR if the scan_mutex
+		 * waiting was interrupted, so only release it if !IS_ERR.
+		 */
+		rcu_read_unlock();
+		mutex_unlock(&scan_mutex);
+		if (v)
+			put_object(v);
+	}
 }
 
 /*
@@ -1211,11 +1268,8 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v)
 	unsigned long flags;
 
 	spin_lock_irqsave(&object->lock, flags);
-	if (!unreferenced_object(object))
-		goto out;
-	print_unreferenced(seq, object);
-	reported_leaks++;
-out:
+	if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
+		print_unreferenced(seq, object);
 	spin_unlock_irqrestore(&object->lock, flags);
 	return 0;
 }
@@ -1229,43 +1283,15 @@ static const struct seq_operations kmemleak_seq_ops = {
 
 static int kmemleak_open(struct inode *inode, struct file *file)
 {
-	int ret = 0;
-
 	if (!atomic_read(&kmemleak_enabled))
 		return -EBUSY;
 
-	ret = mutex_lock_interruptible(&kmemleak_mutex);
-	if (ret < 0)
-		goto out;
-	if (file->f_mode & FMODE_READ) {
-		ret = mutex_lock_interruptible(&scan_mutex);
-		if (ret < 0)
-			goto kmemleak_unlock;
-		ret = seq_open(file, &kmemleak_seq_ops);
-		if (ret < 0)
-			goto scan_unlock;
-	}
-	return ret;
-
-scan_unlock:
-	mutex_unlock(&scan_mutex);
-kmemleak_unlock:
-	mutex_unlock(&kmemleak_mutex);
-out:
-	return ret;
+	return seq_open(file, &kmemleak_seq_ops);
 }
 
 static int kmemleak_release(struct inode *inode, struct file *file)
 {
-	int ret = 0;
-
-	if (file->f_mode & FMODE_READ) {
-		seq_release(inode, file);
-		mutex_unlock(&scan_mutex);
-	}
-	mutex_unlock(&kmemleak_mutex);
-
-	return ret;
+	return seq_release(inode, file);
 }
 
 /*
@@ -1278,21 +1304,24 @@ static int kmemleak_release(struct inode *inode, struct file *file)
  *   scan=off	- stop the automatic memory scanning thread
  *   scan=...	- set the automatic memory scanning period in seconds (0 to
  *		  disable it)
+ *   scan	- trigger a memory scan
  */
 static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
 			      size_t size, loff_t *ppos)
 {
 	char buf[64];
 	int buf_size;
-
-	if (!atomic_read(&kmemleak_enabled))
-		return -EBUSY;
+	int ret;
 
 	buf_size = min(size, (sizeof(buf) - 1));
 	if (strncpy_from_user(buf, user_buf, buf_size) < 0)
 		return -EFAULT;
 	buf[buf_size] = 0;
 
+	ret = mutex_lock_interruptible(&scan_mutex);
+	if (ret < 0)
+		return ret;
+
 	if (strncmp(buf, "off", 3) == 0)
 		kmemleak_disable();
 	else if (strncmp(buf, "stack=on", 8) == 0)
@@ -1305,18 +1334,24 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
 		stop_scan_thread();
 	else if (strncmp(buf, "scan=", 5) == 0) {
 		unsigned long secs;
-		int err;
 
-		err = strict_strtoul(buf + 5, 0, &secs);
-		if (err < 0)
-			return err;
+		ret = strict_strtoul(buf + 5, 0, &secs);
+		if (ret < 0)
+			goto out;
 		stop_scan_thread();
 		if (secs) {
 			jiffies_scan_wait = msecs_to_jiffies(secs * 1000);
 			start_scan_thread();
 		}
-	} else
-		return -EINVAL;
+	} else if (strncmp(buf, "scan", 4) == 0)
+		kmemleak_scan();
+	else
+		ret = -EINVAL;
+
+out:
+	mutex_unlock(&scan_mutex);
+	if (ret < 0)
+		return ret;
 
 	/* ignore the rest of the buffer, only one command at a time */
 	*ppos += size;
@@ -1340,14 +1375,12 @@ static int kmemleak_cleanup_thread(void *arg)
 {
 	struct kmemleak_object *object;
 
-	mutex_lock(&kmemleak_mutex);
+	mutex_lock(&scan_mutex);
 	stop_scan_thread();
-	mutex_unlock(&kmemleak_mutex);
 
-	mutex_lock(&scan_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list)
-		delete_object(object->pointer);
+		delete_object_full(object->pointer);
 	rcu_read_unlock();
 	mutex_unlock(&scan_mutex);
 
@@ -1364,7 +1397,7 @@ static void kmemleak_cleanup(void)
 	cleanup_thread = kthread_run(kmemleak_cleanup_thread, NULL,
 				     "kmemleak-clean");
 	if (IS_ERR(cleanup_thread))
-		pr_warning("kmemleak: Failed to create the clean-up thread\n");
+		pr_warning("Failed to create the clean-up thread\n");
 }
 
 /*
@@ -1404,14 +1437,13 @@ static int kmemleak_boot_config(char *str)
 early_param("kmemleak", kmemleak_boot_config);
 
 /*
- * Kkmemleak initialization.
+ * Kmemleak initialization.
  */
 void __init kmemleak_init(void)
 {
 	int i;
 	unsigned long flags;
 
-	jiffies_scan_yield = msecs_to_jiffies(MSECS_SCAN_YIELD);
 	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
 	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
 
@@ -1443,6 +1475,9 @@ void __init kmemleak_init(void)
 		case KMEMLEAK_FREE:
 			kmemleak_free(log->ptr);
 			break;
+		case KMEMLEAK_FREE_PART:
+			kmemleak_free_part(log->ptr, log->size);
+			break;
 		case KMEMLEAK_NOT_LEAK:
 			kmemleak_not_leak(log->ptr);
 			break;
@@ -1485,11 +1520,10 @@ static int __init kmemleak_late_init(void)
 	dentry = debugfs_create_file("kmemleak", S_IRUGO, NULL, NULL,
 				     &kmemleak_fops);
 	if (!dentry)
-		pr_warning("kmemleak: Failed to create the debugfs kmemleak "
-			   "file\n");
-	mutex_lock(&kmemleak_mutex);
+		pr_warning("Failed to create the debugfs kmemleak file\n");
+	mutex_lock(&scan_mutex);
 	start_scan_thread();
-	mutex_unlock(&kmemleak_mutex);
+	mutex_unlock(&scan_mutex);
 
 	pr_info("Kernel memory leak detector initialized\n");
 
diff --git a/mm/madvise.c b/mm/madvise.c
index b9ce574827c8..76eb4193acdd 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -123,8 +123,7 @@ static long madvise_willneed(struct vm_area_struct * vma,
 		end = vma->vm_end;
 	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-	force_page_cache_readahead(file->f_mapping,
-			file, start, max_sane_readahead(end - start));
+	force_page_cache_readahead(file->f_mapping, file, start, end - start);
 	return 0;
 }
 
@@ -239,12 +238,30 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		break;
 
 	default:
-		error = -EINVAL;
+		BUG();
 		break;
 	}
 	return error;
 }
 
+static int
+madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_DOFORK:
+	case MADV_DONTFORK:
+	case MADV_NORMAL:
+	case MADV_SEQUENTIAL:
+	case MADV_RANDOM:
+	case MADV_REMOVE:
+	case MADV_WILLNEED:
+	case MADV_DONTNEED:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
 /*
  * The madvise(2) system call.
  *
@@ -290,6 +307,9 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int write;
 	size_t len;
 
+	if (!madvise_behavior_valid(behavior))
+		return error;
+
 	write = madvise_need_mmap_write(behavior);
 	if (write)
 		down_write(&current->mm->mmap_sem);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 78eb8552818b..fd4529d86de5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -45,7 +45,7 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
-/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
 int do_swap_account __read_mostly;
 static int really_do_swap_account __initdata = 1; /* for remember boot option*/
 #else
@@ -62,7 +62,8 @@ enum mem_cgroup_stat_index {
 	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
 	 */
 	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
-	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as rss */
+	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as anon rss */
+	MEM_CGROUP_STAT_MAPPED_FILE,  /* # of pages charged as file rss */
 	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
 	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
 
@@ -176,6 +177,9 @@ struct mem_cgroup {
 
 	unsigned int	swappiness;
 
+	/* set when res.limit == memsw.limit */
+	bool		memsw_is_minimum;
+
 	/*
 	 * statistics. This must be placed at the end of memcg.
 	 */
@@ -188,6 +192,7 @@ enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
 	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
+	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
 	NR_CHARGE_TYPE,
 };
 
@@ -570,6 +575,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
 	return 0;
 }
 
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+{
+	unsigned long active;
+	unsigned long inactive;
+
+	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE);
+	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE);
+
+	return (active > inactive);
+}
+
 unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
 				       struct zone *zone,
 				       enum lru_list lru)
@@ -633,6 +649,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
 	int lru = LRU_FILE * !!file + !!active;
+	int ret;
 
 	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
@@ -650,9 +667,19 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 			continue;
 
 		scan++;
-		if (__isolate_lru_page(page, mode, file) == 0) {
+		ret = __isolate_lru_page(page, mode, file);
+		switch (ret) {
+		case 0:
 			list_move(&page->lru, dst);
+			mem_cgroup_del_lru(page);
 			nr_taken++;
+			break;
+		case -EBUSY:
+			/* we don't affect global LRU but rotate in our LRU */
+			mem_cgroup_rotate_lru_list(page, page_lru(page));
+			break;
+		default:
+			break;
 		}
 	}
 
@@ -834,6 +861,10 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	int ret, total = 0;
 	int loop = 0;
 
+	/* If memsw_is_minimum==1, swap-out is of-no-use. */
+	if (root_mem->memsw_is_minimum)
+		noswap = true;
+
 	while (loop < 2) {
 		victim = mem_cgroup_select_victim(root_mem);
 		if (victim == root_mem)
@@ -889,6 +920,44 @@ static void record_last_oom(struct mem_cgroup *mem)
 	mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
 }
 
+/*
+ * Currently used to update mapped file statistics, but the routine can be
+ * generalized to update other statistics as well.
+ */
+void mem_cgroup_update_mapped_file_stat(struct page *page, int val)
+{
+	struct mem_cgroup *mem;
+	struct mem_cgroup_stat *stat;
+	struct mem_cgroup_stat_cpu *cpustat;
+	int cpu;
+	struct page_cgroup *pc;
+
+	if (!page_is_file_cache(page))
+		return;
+
+	pc = lookup_page_cgroup(page);
+	if (unlikely(!pc))
+		return;
+
+	lock_page_cgroup(pc);
+	mem = pc->mem_cgroup;
+	if (!mem)
+		goto done;
+
+	if (!PageCgroupUsed(pc))
+		goto done;
+
+	/*
+	 * Preemption is already disabled, we don't need get_cpu()
+	 */
+	cpu = smp_processor_id();
+	stat = &mem->stat;
+	cpustat = &stat->cpustat[cpu];
+
+	__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE, val);
+done:
+	unlock_page_cgroup(pc);
+}
 
 /*
  * Unlike exported interface, "oom" parameter is added. if oom==true,
@@ -1087,6 +1156,10 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 	struct mem_cgroup_per_zone *from_mz, *to_mz;
 	int nid, zid;
 	int ret = -EBUSY;
+	struct page *page;
+	int cpu;
+	struct mem_cgroup_stat *stat;
+	struct mem_cgroup_stat_cpu *cpustat;
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON(PageLRU(pc->page));
@@ -1107,6 +1180,23 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 
 	res_counter_uncharge(&from->res, PAGE_SIZE);
 	mem_cgroup_charge_statistics(from, pc, false);
+
+	page = pc->page;
+	if (page_is_file_cache(page) && page_mapped(page)) {
+		cpu = smp_processor_id();
+		/* Update mapped_file data for mem_cgroup "from" */
+		stat = &from->stat;
+		cpustat = &stat->cpustat[cpu];
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+						-1);
+
+		/* Update mapped_file data for mem_cgroup "to" */
+		stat = &to->stat;
+		cpustat = &stat->cpustat[cpu];
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_MAPPED_FILE,
+						1);
+	}
+
 	if (do_swap_account)
 		res_counter_uncharge(&from->memsw, PAGE_SIZE);
 	css_put(&from->css);
@@ -1117,6 +1207,12 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 	ret = 0;
 out:
 	unlock_page_cgroup(pc);
+	/*
+	 * We charges against "to" which may not have any tasks. Then, "to"
+	 * can be under rmdir(). But in current implementation, caller of
+	 * this function is just force_empty() and it's garanteed that
+	 * "to" is never removed. So, we don't check rmdir status here.
+	 */
 	return ret;
 }
 
@@ -1338,6 +1434,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 		return;
 	if (!ptr)
 		return;
+	cgroup_exclude_rmdir(&ptr->css);
 	pc = lookup_page_cgroup(page);
 	mem_cgroup_lru_del_before_commit_swapcache(page);
 	__mem_cgroup_commit_charge(ptr, pc, ctype);
@@ -1367,8 +1464,12 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 		}
 		rcu_read_unlock();
 	}
-	/* add this page(page_cgroup) to the LRU we want. */
-
+	/*
+	 * At swapin, we may charge account against cgroup which has no tasks.
+	 * So, rmdir()->pre_destroy() can be called while we do this charge.
+	 * In that case, we need to call pre_destroy() again. check it here.
+	 */
+	cgroup_release_and_wakeup_rmdir(&ptr->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
@@ -1422,6 +1523,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 
 	switch (ctype) {
 	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		if (page_mapped(page))
 			goto unlock_out;
 		break;
@@ -1485,18 +1587,23 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
  * called after __delete_from_swap_cache() and drop "page" account.
  * memcg information is recorded to swap_cgroup of "ent"
  */
-void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
+void
+mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 {
 	struct mem_cgroup *memcg;
+	int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT;
+
+	if (!swapout) /* this was a swap cache but the swap is unused ! */
+		ctype = MEM_CGROUP_CHARGE_TYPE_DROP;
+
+	memcg = __mem_cgroup_uncharge_common(page, ctype);
 
-	memcg = __mem_cgroup_uncharge_common(page,
-					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
 	/* record memcg information */
-	if (do_swap_account && memcg) {
+	if (do_swap_account && swapout && memcg) {
 		swap_cgroup_record(ent, css_id(&memcg->css));
 		mem_cgroup_get(memcg);
 	}
-	if (memcg)
+	if (swapout && memcg)
 		css_put(&memcg->css);
 }
 #endif
@@ -1568,7 +1675,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 
 	if (!mem)
 		return;
-
+	cgroup_exclude_rmdir(&mem->css);
 	/* at migration success, oldpage->mapping is NULL. */
 	if (oldpage->mapping) {
 		target = oldpage;
@@ -1608,6 +1715,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 	 */
 	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
 		mem_cgroup_uncharge_page(target);
+	/*
+	 * At migration, we may charge account against cgroup which has no tasks
+	 * So, rmdir()->pre_destroy() can be called while we do this charge.
+	 * In that case, we need to call pre_destroy() again. check it here.
+	 */
+	cgroup_release_and_wakeup_rmdir(&mem->css);
 }
 
 /*
@@ -1674,6 +1787,12 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 			break;
 		}
 		ret = res_counter_set_limit(&memcg->res, val);
+		if (!ret) {
+			if (memswlimit == val)
+				memcg->memsw_is_minimum = true;
+			else
+				memcg->memsw_is_minimum = false;
+		}
 		mutex_unlock(&set_limit_mutex);
 
 		if (!ret)
@@ -1692,16 +1811,14 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
-int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
-				unsigned long long val)
+static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
+					unsigned long long val)
 {
 	int retry_count;
 	u64 memlimit, oldusage, curusage;
 	int children = mem_cgroup_count_children(memcg);
 	int ret = -EBUSY;
 
-	if (!do_swap_account)
-		return -EINVAL;
 	/* see mem_cgroup_resize_res_limit */
  	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
 	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
@@ -1723,6 +1840,12 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 			break;
 		}
 		ret = res_counter_set_limit(&memcg->memsw, val);
+		if (!ret) {
+			if (memlimit == val)
+				memcg->memsw_is_minimum = true;
+			else
+				memcg->memsw_is_minimum = false;
+		}
 		mutex_unlock(&set_limit_mutex);
 
 		if (!ret)
@@ -1867,7 +1990,7 @@ try_to_free:
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 		}
 
 	}
@@ -1936,8 +2059,7 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 		val = res_counter_read_u64(&mem->res, name);
 		break;
 	case _MEMSWAP:
-		if (do_swap_account)
-			val = res_counter_read_u64(&mem->memsw, name);
+		val = res_counter_read_u64(&mem->memsw, name);
 		break;
 	default:
 		BUG();
@@ -2035,6 +2157,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 enum {
 	MCS_CACHE,
 	MCS_RSS,
+	MCS_MAPPED_FILE,
 	MCS_PGPGIN,
 	MCS_PGPGOUT,
 	MCS_INACTIVE_ANON,
@@ -2055,6 +2178,7 @@ struct {
 } memcg_stat_strings[NR_MCS_STAT] = {
 	{"cache", "total_cache"},
 	{"rss", "total_rss"},
+	{"mapped_file", "total_mapped_file"},
 	{"pgpgin", "total_pgpgin"},
 	{"pgpgout", "total_pgpgout"},
 	{"inactive_anon", "total_inactive_anon"},
@@ -2075,6 +2199,8 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
 	s->stat[MCS_CACHE] += val * PAGE_SIZE;
 	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
 	s->stat[MCS_RSS] += val * PAGE_SIZE;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_MAPPED_FILE);
+	s->stat[MCS_MAPPED_FILE] += val * PAGE_SIZE;
 	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
 	s->stat[MCS_PGPGIN] += val;
 	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
diff --git a/mm/memory.c b/mm/memory.c
index 4126dd16778c..aede2ce3aba4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -135,11 +135,12 @@ void pmd_clear_bad(pmd_t *pmd)
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
  */
-static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+			   unsigned long addr)
 {
 	pgtable_t token = pmd_pgtable(*pmd);
 	pmd_clear(pmd);
-	pte_free_tlb(tlb, token);
+	pte_free_tlb(tlb, token, addr);
 	tlb->mm->nr_ptes--;
 }
 
@@ -157,7 +158,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		free_pte_range(tlb, pmd);
+		free_pte_range(tlb, pmd, addr);
 	} while (pmd++, addr = next, addr != end);
 
 	start &= PUD_MASK;
@@ -173,7 +174,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 
 	pmd = pmd_offset(pud, start);
 	pud_clear(pud);
-	pmd_free_tlb(tlb, pmd);
+	pmd_free_tlb(tlb, pmd, start);
 }
 
 static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -206,7 +207,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 
 	pud = pud_offset(pgd, start);
 	pgd_clear(pgd);
-	pud_free_tlb(tlb, pud);
+	pud_free_tlb(tlb, pud, start);
 }
 
 /*
@@ -1207,8 +1208,8 @@ static inline int use_zero_page(struct vm_area_struct *vma)
 
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int len, int flags,
-		struct page **pages, struct vm_area_struct **vmas)
+		     unsigned long start, int nr_pages, int flags,
+		     struct page **pages, struct vm_area_struct **vmas)
 {
 	int i;
 	unsigned int vm_flags = 0;
@@ -1217,7 +1218,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
 	int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
 
-	if (len <= 0)
+	if (nr_pages <= 0)
 		return 0;
 	/* 
 	 * Require read or write permissions.
@@ -1269,7 +1270,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				vmas[i] = gate_vma;
 			i++;
 			start += PAGE_SIZE;
-			len--;
+			nr_pages--;
 			continue;
 		}
 
@@ -1280,7 +1281,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 		if (is_vm_hugetlb_page(vma)) {
 			i = follow_hugetlb_page(mm, vma, pages, vmas,
-						&start, &len, i, write);
+						&start, &nr_pages, i, write);
 			continue;
 		}
 
@@ -1310,8 +1311,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			cond_resched();
 			while (!(page = follow_page(vma, start, foll_flags))) {
 				int ret;
+
 				ret = handle_mm_fault(mm, vma, start,
-						foll_flags & FOLL_WRITE);
+					(foll_flags & FOLL_WRITE) ?
+					FAULT_FLAG_WRITE : 0);
+
 				if (ret & VM_FAULT_ERROR) {
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
@@ -1354,14 +1358,64 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				vmas[i] = vma;
 			i++;
 			start += PAGE_SIZE;
-			len--;
-		} while (len && start < vma->vm_end);
-	} while (len);
+			nr_pages--;
+		} while (nr_pages && start < vma->vm_end);
+	} while (nr_pages);
 	return i;
 }
 
+/**
+ * get_user_pages() - pin user pages in memory
+ * @tsk:	task_struct of target task
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to by the caller
+ * @force:	whether to force write access even if user mapping is
+ *		readonly. This will result in the page being COWed even
+ *		in MAP_SHARED mappings. You do not want this.
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with. vmas will only
+ * remain valid while mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If write=0, the page must not be written to. If the page is written to,
+ * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
+ * after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, int len, int write, int force,
+		unsigned long start, int nr_pages, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = 0;
@@ -1371,9 +1425,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= GUP_FLAGS_FORCE;
 
-	return __get_user_pages(tsk, mm,
-				start, len, flags,
-				pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
 }
 
 EXPORT_SYMBOL(get_user_pages);
@@ -2446,7 +2498,7 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
  */
 static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		int write_access, pte_t orig_pte)
+		unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
 	struct page *page;
@@ -2466,7 +2518,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
 	page = lookup_swap_cache(entry);
 	if (!page) {
-		grab_swap_token(); /* Contend for token _before_ read-in */
+		grab_swap_token(mm); /* Contend for token _before_ read-in */
 		page = swapin_readahead(entry,
 					GFP_HIGHUSER_MOVABLE, vma, address);
 		if (!page) {
@@ -2522,9 +2574,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	inc_mm_counter(mm, anon_rss);
 	pte = mk_pte(page, vma->vm_page_prot);
-	if (write_access && reuse_swap_page(page)) {
+	if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
-		write_access = 0;
+		flags &= ~FAULT_FLAG_WRITE;
 	}
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
@@ -2537,7 +2589,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		try_to_free_swap(page);
 	unlock_page(page);
 
-	if (write_access) {
+	if (flags & FAULT_FLAG_WRITE) {
 		ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
 		if (ret & VM_FAULT_ERROR)
 			ret &= VM_FAULT_ERROR;
@@ -2566,7 +2618,7 @@ out_page:
  */
 static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		int write_access)
+		unsigned int flags)
 {
 	struct page *page;
 	spinlock_t *ptl;
@@ -2726,7 +2778,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * due to the bad i386 page protection. But it's valid
 	 * for other architectures too.
 	 *
-	 * Note that if write_access is true, we either now have
+	 * Note that if FAULT_FLAG_WRITE is set, we either now have
 	 * an exclusive copy of the page, or this is a shared mapping,
 	 * so we can make it writable and dirty to avoid having to
 	 * handle that later.
@@ -2797,11 +2849,10 @@ unwritable_page:
 
 static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		int write_access, pte_t orig_pte)
+		unsigned int flags, pte_t orig_pte)
 {
 	pgoff_t pgoff = (((address & PAGE_MASK)
 			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-	unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
 
 	pte_unmap(page_table);
 	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
@@ -2818,12 +2869,12 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		int write_access, pte_t orig_pte)
+		unsigned int flags, pte_t orig_pte)
 {
-	unsigned int flags = FAULT_FLAG_NONLINEAR |
-				(write_access ? FAULT_FLAG_WRITE : 0);
 	pgoff_t pgoff;
 
+	flags |= FAULT_FLAG_NONLINEAR;
+
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
 		return 0;
 
@@ -2854,7 +2905,7 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static inline int handle_pte_fault(struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long address,
-		pte_t *pte, pmd_t *pmd, int write_access)
+		pte_t *pte, pmd_t *pmd, unsigned int flags)
 {
 	pte_t entry;
 	spinlock_t *ptl;
@@ -2865,30 +2916,30 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 			if (vma->vm_ops) {
 				if (likely(vma->vm_ops->fault))
 					return do_linear_fault(mm, vma, address,
-						pte, pmd, write_access, entry);
+						pte, pmd, flags, entry);
 			}
 			return do_anonymous_page(mm, vma, address,
-						 pte, pmd, write_access);
+						 pte, pmd, flags);
 		}
 		if (pte_file(entry))
 			return do_nonlinear_fault(mm, vma, address,
-					pte, pmd, write_access, entry);
+					pte, pmd, flags, entry);
 		return do_swap_page(mm, vma, address,
-					pte, pmd, write_access, entry);
+					pte, pmd, flags, entry);
 	}
 
 	ptl = pte_lockptr(mm, pmd);
 	spin_lock(ptl);
 	if (unlikely(!pte_same(*pte, entry)))
 		goto unlock;
-	if (write_access) {
+	if (flags & FAULT_FLAG_WRITE) {
 		if (!pte_write(entry))
 			return do_wp_page(mm, vma, address,
 					pte, pmd, ptl, entry);
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
-	if (ptep_set_access_flags(vma, address, pte, entry, write_access)) {
+	if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
 		update_mmu_cache(vma, address, entry);
 	} else {
 		/*
@@ -2897,7 +2948,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		 * This still avoids useless tlb flushes for .text page faults
 		 * with threads.
 		 */
-		if (write_access)
+		if (flags & FAULT_FLAG_WRITE)
 			flush_tlb_page(vma, address);
 	}
 unlock:
@@ -2909,7 +2960,7 @@ unlock:
  * By the time we get here, we already hold the mm semaphore
  */
 int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, int write_access)
+		unsigned long address, unsigned int flags)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -2921,7 +2972,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	count_vm_event(PGFAULT);
 
 	if (unlikely(is_vm_hugetlb_page(vma)))
-		return hugetlb_fault(mm, vma, address, write_access);
+		return hugetlb_fault(mm, vma, address, flags);
 
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
@@ -2934,7 +2985,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte)
 		return VM_FAULT_OOM;
 
-	return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
 
 #ifndef __PAGETABLE_PUD_FOLDED
@@ -3053,22 +3104,13 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
-#ifdef CONFIG_HAVE_IOREMAP_PROT
-int follow_phys(struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags,
-		unsigned long *prot, resource_size_t *phys)
+static int follow_pte(struct mm_struct *mm, unsigned long address,
+		pte_t **ptepp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
-	resource_size_t phys_addr = 0;
-	struct mm_struct *mm = vma->vm_mm;
-	int ret = -EINVAL;
-
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
-		goto out;
+	pte_t *ptep;
 
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
@@ -3086,22 +3128,71 @@ int follow_phys(struct vm_area_struct *vma,
 	if (pmd_huge(*pmd))
 		goto out;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
 	if (!ptep)
 		goto out;
+	if (!pte_present(*ptep))
+		goto unlock;
+	*ptepp = ptep;
+	return 0;
+unlock:
+	pte_unmap_unlock(ptep, *ptlp);
+out:
+	return -EINVAL;
+}
+
+/**
+ * follow_pfn - look up PFN at a user virtual address
+ * @vma: memory mapping
+ * @address: user virtual address
+ * @pfn: location to store found PFN
+ *
+ * Only IO mappings and raw PFN mappings are allowed.
+ *
+ * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ */
+int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+	unsigned long *pfn)
+{
+	int ret = -EINVAL;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return ret;
+
+	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
+	if (ret)
+		return ret;
+	*pfn = pte_pfn(*ptep);
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+int follow_phys(struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags,
+		unsigned long *prot, resource_size_t *phys)
+{
+	int ret = -EINVAL;
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		goto out;
 
+	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+		goto out;
 	pte = *ptep;
-	if (!pte_present(pte))
-		goto unlock;
+
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
-	phys_addr = pte_pfn(pte);
-	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
 
 	*prot = pgprot_val(pte_pgprot(pte));
-	*phys = phys_addr;
-	ret = 0;
+	*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
 
+	ret = 0;
 unlock:
 	pte_unmap_unlock(ptep, ptl);
 out:
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c083cf5fd6df..e4412a676c88 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -422,7 +422,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 
-	setup_per_zone_pages_min();
+	setup_per_zone_wmarks();
+	calculate_zone_inactive_ratio(zone);
 	if (onlined_pages) {
 		kswapd_run(zone_to_nid(zone));
 		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -832,6 +833,9 @@ repeat:
 	totalram_pages -= offlined_pages;
 	num_physpages -= offlined_pages;
 
+	setup_per_zone_wmarks();
+	calculate_zone_inactive_ratio(zone);
+
 	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3eb4a6fdc043..7dd9d9f80694 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -182,13 +182,58 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
 	return 0;
 }
 
-/* Create a new policy */
+/*
+ * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
+ * any, for the new policy.  mpol_new() has already validated the nodes
+ * parameter with respect to the policy mode and flags.  But, we need to
+ * handle an empty nodemask with MPOL_PREFERRED here.
+ *
+ * Must be called holding task's alloc_lock to protect task's mems_allowed
+ * and mempolicy.  May also be called holding the mmap_semaphore for write.
+ */
+static int mpol_set_nodemask(struct mempolicy *pol,
+		     const nodemask_t *nodes, struct nodemask_scratch *nsc)
+{
+	int ret;
+
+	/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
+	if (pol == NULL)
+		return 0;
+	/* Check N_HIGH_MEMORY */
+	nodes_and(nsc->mask1,
+		  cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]);
+
+	VM_BUG_ON(!nodes);
+	if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
+		nodes = NULL;	/* explicit local allocation */
+	else {
+		if (pol->flags & MPOL_F_RELATIVE_NODES)
+			mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
+		else
+			nodes_and(nsc->mask2, *nodes, nsc->mask1);
+
+		if (mpol_store_user_nodemask(pol))
+			pol->w.user_nodemask = *nodes;
+		else
+			pol->w.cpuset_mems_allowed =
+						cpuset_current_mems_allowed;
+	}
+
+	if (nodes)
+		ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
+	else
+		ret = mpol_ops[pol->mode].create(pol, NULL);
+	return ret;
+}
+
+/*
+ * This function just creates a new policy, does some check and simple
+ * initialization. You must invoke mpol_set_nodemask() to set nodes.
+ */
 static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 				  nodemask_t *nodes)
 {
 	struct mempolicy *policy;
-	nodemask_t cpuset_context_nmask;
-	int ret;
 
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
 		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
@@ -210,7 +255,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 			if (((flags & MPOL_F_STATIC_NODES) ||
 			     (flags & MPOL_F_RELATIVE_NODES)))
 				return ERR_PTR(-EINVAL);
-			nodes = NULL;	/* flag local alloc */
 		}
 	} else if (nodes_empty(*nodes))
 		return ERR_PTR(-EINVAL);
@@ -221,30 +265,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	policy->mode = mode;
 	policy->flags = flags;
 
-	if (nodes) {
-		/*
-		 * cpuset related setup doesn't apply to local allocation
-		 */
-		cpuset_update_task_memory_state();
-		if (flags & MPOL_F_RELATIVE_NODES)
-			mpol_relative_nodemask(&cpuset_context_nmask, nodes,
-					       &cpuset_current_mems_allowed);
-		else
-			nodes_and(cpuset_context_nmask, *nodes,
-				  cpuset_current_mems_allowed);
-		if (mpol_store_user_nodemask(policy))
-			policy->w.user_nodemask = *nodes;
-		else
-			policy->w.cpuset_mems_allowed =
-						cpuset_mems_allowed(current);
-	}
-
-	ret = mpol_ops[mode].create(policy,
-				nodes ? &cpuset_context_nmask : NULL);
-	if (ret < 0) {
-		kmem_cache_free(policy_cache, policy);
-		return ERR_PTR(ret);
-	}
 	return policy;
 }
 
@@ -324,6 +344,8 @@ static void mpol_rebind_policy(struct mempolicy *pol,
 /*
  * Wrapper for mpol_rebind_policy() that just requires task
  * pointer, and updates task mempolicy.
+ *
+ * Called with task's alloc_lock held.
  */
 
 void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
@@ -600,13 +622,19 @@ static void mpol_set_task_struct_flag(void)
 static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
 {
-	struct mempolicy *new;
+	struct mempolicy *new, *old;
 	struct mm_struct *mm = current->mm;
+	NODEMASK_SCRATCH(scratch);
+	int ret;
 
-	new = mpol_new(mode, flags, nodes);
-	if (IS_ERR(new))
-		return PTR_ERR(new);
+	if (!scratch)
+		return -ENOMEM;
 
+	new = mpol_new(mode, flags, nodes);
+	if (IS_ERR(new)) {
+		ret = PTR_ERR(new);
+		goto out;
+	}
 	/*
 	 * prevent changing our mempolicy while show_numa_maps()
 	 * is using it.
@@ -615,20 +643,36 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	 */
 	if (mm)
 		down_write(&mm->mmap_sem);
-	mpol_put(current->mempolicy);
+	task_lock(current);
+	ret = mpol_set_nodemask(new, nodes, scratch);
+	if (ret) {
+		task_unlock(current);
+		if (mm)
+			up_write(&mm->mmap_sem);
+		mpol_put(new);
+		goto out;
+	}
+	old = current->mempolicy;
 	current->mempolicy = new;
 	mpol_set_task_struct_flag();
 	if (new && new->mode == MPOL_INTERLEAVE &&
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
+	task_unlock(current);
 	if (mm)
 		up_write(&mm->mmap_sem);
 
-	return 0;
+	mpol_put(old);
+	ret = 0;
+out:
+	NODEMASK_SCRATCH_FREE(scratch);
+	return ret;
 }
 
 /*
  * Return nodemask for policy for get_mempolicy() query
+ *
+ * Called with task's alloc_lock held
  */
 static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
 {
@@ -674,7 +718,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	struct vm_area_struct *vma = NULL;
 	struct mempolicy *pol = current->mempolicy;
 
-	cpuset_update_task_memory_state();
 	if (flags &
 		~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
 		return -EINVAL;
@@ -683,7 +726,9 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 		if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
 			return -EINVAL;
 		*policy = 0;	/* just so it's initialized */
+		task_lock(current);
 		*nmask  = cpuset_current_mems_allowed;
+		task_unlock(current);
 		return 0;
 	}
 
@@ -738,8 +783,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	}
 
 	err = 0;
-	if (nmask)
+	if (nmask) {
+		task_lock(current);
 		get_policy_nodemask(pol, nmask);
+		task_unlock(current);
+	}
 
  out:
 	mpol_cond_put(pol);
@@ -767,7 +815,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 
 static struct page *new_node_page(struct page *page, unsigned long node, int **x)
 {
-	return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
+	return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
 }
 
 /*
@@ -978,7 +1026,23 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (err)
 			return err;
 	}
-	down_write(&mm->mmap_sem);
+	{
+		NODEMASK_SCRATCH(scratch);
+		if (scratch) {
+			down_write(&mm->mmap_sem);
+			task_lock(current);
+			err = mpol_set_nodemask(new, nmask, scratch);
+			task_unlock(current);
+			if (err)
+				up_write(&mm->mmap_sem);
+		} else
+			err = -ENOMEM;
+		NODEMASK_SCRATCH_FREE(scratch);
+	}
+	if (err) {
+		mpol_put(new);
+		return err;
+	}
 	vma = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
@@ -1545,8 +1609,6 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
 
-	cpuset_update_task_memory_state();
-
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
@@ -1593,8 +1655,6 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 
-	if ((gfp & __GFP_WAIT) && !in_interrupt())
-		cpuset_update_task_memory_state();
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
@@ -1851,27 +1911,46 @@ restart:
  * Install non-NULL @mpol in inode's shared policy rb-tree.
  * On entry, the current task has a reference on a non-NULL @mpol.
  * This must be released on exit.
+ * This is called at get_inode() calls and we can use GFP_KERNEL.
  */
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 {
+	int ret;
+
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
 	spin_lock_init(&sp->lock);
 
 	if (mpol) {
 		struct vm_area_struct pvma;
 		struct mempolicy *new;
+		NODEMASK_SCRATCH(scratch);
 
+		if (!scratch)
+			return;
 		/* contextualize the tmpfs mount point mempolicy */
 		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
-		mpol_put(mpol);	/* drop our ref on sb mpol */
-		if (IS_ERR(new))
+		if (IS_ERR(new)) {
+			mpol_put(mpol);	/* drop our ref on sb mpol */
+			NODEMASK_SCRATCH_FREE(scratch);
 			return;		/* no valid nodemask intersection */
+		}
+
+		task_lock(current);
+		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch);
+		task_unlock(current);
+		mpol_put(mpol);	/* drop our ref on sb mpol */
+		if (ret) {
+			NODEMASK_SCRATCH_FREE(scratch);
+			mpol_put(new);
+			return;
+		}
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
 		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
 		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
 		mpol_put(new);			/* drop initial ref */
+		NODEMASK_SCRATCH_FREE(scratch);
 	}
 }
 
@@ -2086,8 +2165,24 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	new = mpol_new(mode, mode_flags, &nodes);
 	if (IS_ERR(new))
 		err = 1;
-	else if (no_context)
-		new->w.user_nodemask = nodes;	/* save for contextualization */
+	else {
+		int ret;
+		NODEMASK_SCRATCH(scratch);
+		if (scratch) {
+			task_lock(current);
+			ret = mpol_set_nodemask(new, &nodes, scratch);
+			task_unlock(current);
+		} else
+			ret = -ENOMEM;
+		NODEMASK_SCRATCH_FREE(scratch);
+		if (ret) {
+			err = 1;
+			mpol_put(new);
+		} else if (no_context) {
+			/* save for contextualization */
+			new->w.user_nodemask = nodes;
+		}
+	}
 
 out:
 	/* Restore string for error message */
diff --git a/mm/mempool.c b/mm/mempool.c
index a46eb1b4bb66..32e75d400503 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -303,14 +303,14 @@ EXPORT_SYMBOL(mempool_free_slab);
  */
 void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
 {
-	size_t size = (size_t)(long)pool_data;
+	size_t size = (size_t)pool_data;
 	return kmalloc(size, gfp_mask);
 }
 EXPORT_SYMBOL(mempool_kmalloc);
 
 void *mempool_kzalloc(gfp_t gfp_mask, void *pool_data)
 {
-	size_t size = (size_t) pool_data;
+	size_t size = (size_t)pool_data;
 	return kzalloc(size, gfp_mask);
 }
 EXPORT_SYMBOL(mempool_kzalloc);
diff --git a/mm/migrate.c b/mm/migrate.c
index 068655d8f883..939888f9ddab 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -802,7 +802,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 
 	*result = &pm->status;
 
-	return alloc_pages_node(pm->node,
+	return alloc_pages_exact_node(pm->node,
 				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
 }
 
@@ -820,7 +820,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 	struct page_to_node *pp;
 	LIST_HEAD(pagelist);
 
-	migrate_prep();
 	down_read(&mm->mmap_sem);
 
 	/*
@@ -907,6 +906,9 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
 	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
 	if (!pm)
 		goto out;
+
+	migrate_prep();
+
 	/*
 	 * Store a chunk of page_to_node array in a page,
 	 * but keep the last one as a marker
diff --git a/mm/mlock.c b/mm/mlock.c
index ac130433c7d3..45eb650b9654 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -31,7 +31,6 @@ int can_do_mlock(void)
 }
 EXPORT_SYMBOL(can_do_mlock);
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * Mlocked pages are marked with PageMlocked() flag for efficient testing
  * in vmscan and, possibly, the fault path; and to support semi-accurate
@@ -261,27 +260,6 @@ static int __mlock_posix_error_return(long retval)
 	return retval;
 }
 
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-/*
- * Just make pages present if VM_LOCKED.  No-op if unlocking.
- */
-static long __mlock_vma_pages_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   int mlock)
-{
-	if (mlock && (vma->vm_flags & VM_LOCKED))
-		return make_pages_present(start, end);
-	return 0;
-}
-
-static inline int __mlock_posix_error_return(long retval)
-{
-	return 0;
-}
-
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
 /**
  * mlock_vma_pages_range() - mlock pages in specified vma range.
  * @vma - the vma containing the specfied address range
diff --git a/mm/mmap.c b/mm/mmap.c
index 34579b23ebd5..8101de490c73 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -88,9 +88,6 @@ int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 struct percpu_counter vm_committed_as;
 
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
 /*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fd2ad5da98e..4bde489ec431 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,9 +69,6 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
-/* amount of vm to protect from userspace access */
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-
 atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
@@ -173,8 +170,8 @@ unsigned int kobjsize(const void *objp)
 }
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int len, int flags,
-		struct page **pages, struct vm_area_struct **vmas)
+		     unsigned long start, int nr_pages, int flags,
+		     struct page **pages, struct vm_area_struct **vmas)
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
@@ -189,7 +186,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
 	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
 
-	for (i = 0; i < len; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		vma = find_vma(mm, start);
 		if (!vma)
 			goto finish_or_fault;
@@ -224,7 +221,7 @@ finish_or_fault:
  * - don't permit access to VMAs that don't support it, such as I/O mappings
  */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-	unsigned long start, int len, int write, int force,
+	unsigned long start, int nr_pages, int write, int force,
 	struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = 0;
@@ -234,12 +231,31 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= GUP_FLAGS_FORCE;
 
-	return __get_user_pages(tsk, mm,
-				start, len, flags,
-				pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
 }
 EXPORT_SYMBOL(get_user_pages);
 
+/**
+ * follow_pfn - look up PFN at a user virtual address
+ * @vma: memory mapping
+ * @address: user virtual address
+ * @pfn: location to store found PFN
+ *
+ * Only IO mappings and raw PFN mappings are allowed.
+ *
+ * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ */
+int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+	unsigned long *pfn)
+{
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return -EINVAL;
+
+	*pfn = address >> PAGE_SHIFT;
+	return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
 DEFINE_RWLOCK(vmlist_lock);
 struct vm_struct *vmlist;
 
@@ -903,6 +919,10 @@ static int validate_mmap_request(struct file *file,
 		if (!file->f_op->read)
 			capabilities &= ~BDI_CAP_MAP_COPY;
 
+		/* The file shall have been opened with read permission. */
+		if (!(file->f_mode & FMODE_READ))
+			return -EACCES;
+
 		if (flags & MAP_SHARED) {
 			/* do checks for writing, appending and locking */
 			if ((prot & PROT_WRITE) &&
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bb553c3e955d..81627ebcd313 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -265,18 +265,19 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi,
  * This avoids exceeding the total dirty_limit when the floating averages
  * fluctuate too quickly.
  */
-static void
-clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
+static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
+		unsigned long dirty, unsigned long *pbdi_dirty)
 {
-	long avail_dirty;
+	unsigned long avail_dirty;
 
-	avail_dirty = dirty -
-		(global_page_state(NR_FILE_DIRTY) +
+	avail_dirty = global_page_state(NR_FILE_DIRTY) +
 		 global_page_state(NR_WRITEBACK) +
 		 global_page_state(NR_UNSTABLE_NFS) +
-		 global_page_state(NR_WRITEBACK_TEMP));
+		 global_page_state(NR_WRITEBACK_TEMP);
 
-	if (avail_dirty < 0)
+	if (avail_dirty < dirty)
+		avail_dirty = dirty - avail_dirty;
+	else
 		avail_dirty = 0;
 
 	avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
@@ -299,10 +300,10 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
  *
  *   dirty -= (dirty/8) * p_{t}
  */
-static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 {
 	long numerator, denominator;
-	long dirty = *pdirty;
+	unsigned long dirty = *pdirty;
 	u64 inv = dirty >> 3;
 
 	task_dirties_fraction(tsk, &numerator, &denominator);
@@ -540,8 +541,11 @@ static void balance_dirty_pages(struct address_space *mapping)
 		 * filesystems (i.e. NFS) in which data may have been
 		 * written to the server's write cache, but has not yet
 		 * been flushed to permanent storage.
+		 * Only move pages to writeback if this bdi is over its
+		 * threshold otherwise wait until the disk writes catch
+		 * up.
 		 */
-		if (bdi_nr_reclaimable) {
+		if (bdi_nr_reclaimable > bdi_thresh) {
 			writeback_inodes(&wbc);
 			pages_written += write_chunk - wbc.nr_to_write;
 			get_dirty_limits(&background_thresh, &dirty_thresh,
@@ -571,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
-		congestion_wait(WRITE, HZ/10);
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
 	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -665,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
                 if (global_page_state(NR_UNSTABLE_NFS) +
 			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
-                congestion_wait(WRITE, HZ/10);
+                congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * The caller might hold locks which can prevent IO completion
@@ -711,7 +715,7 @@ static void background_writeout(unsigned long _min_pages)
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;
 		}
@@ -783,7 +787,7 @@ static void wb_kupdate(unsigned long arg)
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;	/* All the old data is written */
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17d5f539a9aa..5cc986eb9f6f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -23,6 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/kmemcheck.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <linux/pagevec.h>
@@ -72,6 +73,7 @@ unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
 unsigned long highest_memmap_pfn __read_mostly;
 int percpu_pagelist_fraction;
+gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 int pageblock_order __read_mostly;
@@ -161,17 +163,25 @@ static unsigned long __meminitdata dma_reserve;
 
 #if MAX_NUMNODES > 1
 int nr_node_ids __read_mostly = MAX_NUMNODES;
+int nr_online_nodes __read_mostly = 1;
 EXPORT_SYMBOL(nr_node_ids);
+EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
 int page_group_by_mobility_disabled __read_mostly;
 
 static void set_pageblock_migratetype(struct page *page, int migratetype)
 {
+
+	if (unlikely(page_group_by_mobility_disabled))
+		migratetype = MIGRATE_UNMOVABLE;
+
 	set_pageblock_flags_group(page, (unsigned long)migratetype,
 					PB_migrate, PB_migrate_end);
 }
 
+bool oom_killer_disabled __read_mostly;
+
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
@@ -294,23 +304,6 @@ void prep_compound_page(struct page *page, unsigned long order)
 	}
 }
 
-#ifdef CONFIG_HUGETLBFS
-void prep_compound_gigantic_page(struct page *page, unsigned long order)
-{
-	int i;
-	int nr_pages = 1 << order;
-	struct page *p = page + 1;
-
-	set_compound_page_dtor(page, free_compound_page);
-	set_compound_order(page, order);
-	__SetPageHead(page);
-	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-		__SetPageTail(p);
-		p->first_page = page;
-	}
-}
-#endif
-
 static int destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;
@@ -417,7 +410,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
 		return 0;
 
 	if (PageBuddy(buddy) && page_order(buddy) == order) {
-		BUG_ON(page_count(buddy) != 0);
+		VM_BUG_ON(page_count(buddy) != 0);
 		return 1;
 	}
 	return 0;
@@ -448,22 +441,22 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  */
 
 static inline void __free_one_page(struct page *page,
-		struct zone *zone, unsigned int order)
+		struct zone *zone, unsigned int order,
+		int migratetype)
 {
 	unsigned long page_idx;
-	int order_size = 1 << order;
-	int migratetype = get_pageblock_migratetype(page);
 
 	if (unlikely(PageCompound(page)))
 		if (unlikely(destroy_compound_page(page, order)))
 			return;
 
+	VM_BUG_ON(migratetype == -1);
+
 	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
 
-	VM_BUG_ON(page_idx & (order_size - 1));
+	VM_BUG_ON(page_idx & ((1 << order) - 1));
 	VM_BUG_ON(bad_range(zone, page));
 
-	__mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
 	while (order < MAX_ORDER-1) {
 		unsigned long combined_idx;
 		struct page *buddy;
@@ -487,12 +480,26 @@ static inline void __free_one_page(struct page *page,
 	zone->free_area[order].nr_free++;
 }
 
+#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
+/*
+ * free_page_mlock() -- clean up attempts to free and mlocked() page.
+ * Page should not be on lru, so no need to fix that up.
+ * free_pages_check() will verify...
+ */
+static inline void free_page_mlock(struct page *page)
+{
+	__dec_zone_page_state(page, NR_MLOCK);
+	__count_vm_event(UNEVICTABLE_MLOCKFREED);
+}
+#else
+static void free_page_mlock(struct page *page) { }
+#endif
+
 static inline int free_pages_check(struct page *page)
 {
-	free_page_mlock(page);
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
-		(page_count(page) != 0)  |
+		(atomic_read(&page->_count) != 0) |
 		(page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
 		bad_page(page);
 		return 1;
@@ -519,6 +526,8 @@ static void free_pages_bulk(struct zone *zone, int count,
 	spin_lock(&zone->lock);
 	zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
 	zone->pages_scanned = 0;
+
+	__mod_zone_page_state(zone, NR_FREE_PAGES, count << order);
 	while (count--) {
 		struct page *page;
 
@@ -526,17 +535,20 @@ static void free_pages_bulk(struct zone *zone, int count,
 		page = list_entry(list->prev, struct page, lru);
 		/* have to delete it as __free_one_page list manipulates */
 		list_del(&page->lru);
-		__free_one_page(page, zone, order);
+		__free_one_page(page, zone, order, page_private(page));
 	}
 	spin_unlock(&zone->lock);
 }
 
-static void free_one_page(struct zone *zone, struct page *page, int order)
+static void free_one_page(struct zone *zone, struct page *page, int order,
+				int migratetype)
 {
 	spin_lock(&zone->lock);
 	zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
 	zone->pages_scanned = 0;
-	__free_one_page(page, zone, order);
+
+	__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+	__free_one_page(page, zone, order, migratetype);
 	spin_unlock(&zone->lock);
 }
 
@@ -545,6 +557,9 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	unsigned long flags;
 	int i;
 	int bad = 0;
+	int wasMlocked = TestClearPageMlocked(page);
+
+	kmemcheck_free_shadow(page, order);
 
 	for (i = 0 ; i < (1 << order) ; ++i)
 		bad += free_pages_check(page + i);
@@ -560,8 +575,11 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	kernel_map_pages(page, 1 << order, 0);
 
 	local_irq_save(flags);
+	if (unlikely(wasMlocked))
+		free_page_mlock(page);
 	__count_vm_events(PGFREE, 1 << order);
-	free_one_page(page_zone(page), page, order);
+	free_one_page(page_zone(page), page, order,
+					get_pageblock_migratetype(page));
 	local_irq_restore(flags);
 }
 
@@ -632,7 +650,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
-		(page_count(page) != 0)  |
+		(atomic_read(&page->_count) != 0)  |
 		(page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
 		bad_page(page);
 		return 1;
@@ -657,7 +675,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
  * Go through the free lists for the given migratetype and remove
  * the smallest available page from the freelists
  */
-static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
+static inline
+struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 						int migratetype)
 {
 	unsigned int current_order;
@@ -675,7 +694,6 @@ static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		list_del(&page->lru);
 		rmv_page_order(page);
 		area->nr_free--;
-		__mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order));
 		expand(zone, page, order, current_order, area, migratetype);
 		return page;
 	}
@@ -766,8 +784,8 @@ static int move_freepages_block(struct zone *zone, struct page *page,
 }
 
 /* Remove an element from the buddy allocator from the fallback list */
-static struct page *__rmqueue_fallback(struct zone *zone, int order,
-						int start_migratetype)
+static inline struct page *
+__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 {
 	struct free_area * area;
 	int current_order;
@@ -815,8 +833,6 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order,
 			/* Remove the page from the freelists */
 			list_del(&page->lru);
 			rmv_page_order(page);
-			__mod_zone_page_state(zone, NR_FREE_PAGES,
-							-(1UL << order));
 
 			if (current_order == pageblock_order)
 				set_pageblock_migratetype(page,
@@ -827,8 +843,7 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order,
 		}
 	}
 
-	/* Use MIGRATE_RESERVE rather than fail an allocation */
-	return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
+	return NULL;
 }
 
 /*
@@ -840,11 +855,23 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
 {
 	struct page *page;
 
+retry_reserve:
 	page = __rmqueue_smallest(zone, order, migratetype);
 
-	if (unlikely(!page))
+	if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
 		page = __rmqueue_fallback(zone, order, migratetype);
 
+		/*
+		 * Use MIGRATE_RESERVE rather than fail an allocation. goto
+		 * is used because __rmqueue_smallest is an inline function
+		 * and we want just one call site
+		 */
+		if (!page) {
+			migratetype = MIGRATE_RESERVE;
+			goto retry_reserve;
+		}
+	}
+
 	return page;
 }
 
@@ -855,7 +882,7 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order,
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order, 
 			unsigned long count, struct list_head *list,
-			int migratetype)
+			int migratetype, int cold)
 {
 	int i;
 	
@@ -874,10 +901,14 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 * merge IO requests if the physical pages are ordered
 		 * properly.
 		 */
-		list_add(&page->lru, list);
+		if (likely(cold == 0))
+			list_add(&page->lru, list);
+		else
+			list_add_tail(&page->lru, list);
 		set_page_private(page, migratetype);
 		list = &page->lru;
 	}
+	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
 	spin_unlock(&zone->lock);
 	return i;
 }
@@ -993,6 +1024,9 @@ static void free_hot_cold_page(struct page *page, int cold)
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
 	unsigned long flags;
+	int wasMlocked = TestClearPageMlocked(page);
+
+	kmemcheck_free_shadow(page, 0);
 
 	if (PageAnon(page))
 		page->mapping = NULL;
@@ -1007,13 +1041,16 @@ static void free_hot_cold_page(struct page *page, int cold)
 	kernel_map_pages(page, 1, 0);
 
 	pcp = &zone_pcp(zone, get_cpu())->pcp;
+	set_page_private(page, get_pageblock_migratetype(page));
 	local_irq_save(flags);
+	if (unlikely(wasMlocked))
+		free_page_mlock(page);
 	__count_vm_event(PGFREE);
+
 	if (cold)
 		list_add_tail(&page->lru, &pcp->list);
 	else
 		list_add(&page->lru, &pcp->list);
-	set_page_private(page, get_pageblock_migratetype(page));
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
 		free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
@@ -1047,6 +1084,16 @@ void split_page(struct page *page, unsigned int order)
 
 	VM_BUG_ON(PageCompound(page));
 	VM_BUG_ON(!page_count(page));
+
+#ifdef CONFIG_KMEMCHECK
+	/*
+	 * Split shadow pages too, because free(page[0]) would
+	 * otherwise free the whole shadow.
+	 */
+	if (kmemcheck_page_is_tracked(page))
+		split_page(virt_to_page(page[0].shadow), order);
+#endif
+
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 }
@@ -1056,14 +1103,15 @@ void split_page(struct page *page, unsigned int order)
  * we cheat by calling it from here, in the order > 0 path.  Saves a branch
  * or two.
  */
-static struct page *buffered_rmqueue(struct zone *preferred_zone,
-			struct zone *zone, int order, gfp_t gfp_flags)
+static inline
+struct page *buffered_rmqueue(struct zone *preferred_zone,
+			struct zone *zone, int order, gfp_t gfp_flags,
+			int migratetype)
 {
 	unsigned long flags;
 	struct page *page;
 	int cold = !!(gfp_flags & __GFP_COLD);
 	int cpu;
-	int migratetype = allocflags_to_migratetype(gfp_flags);
 
 again:
 	cpu  = get_cpu();
@@ -1074,7 +1122,8 @@ again:
 		local_irq_save(flags);
 		if (!pcp->count) {
 			pcp->count = rmqueue_bulk(zone, 0,
-					pcp->batch, &pcp->list, migratetype);
+					pcp->batch, &pcp->list,
+					migratetype, cold);
 			if (unlikely(!pcp->count))
 				goto failed;
 		}
@@ -1093,15 +1142,30 @@ again:
 		/* Allocate more to the pcp list if necessary */
 		if (unlikely(&page->lru == &pcp->list)) {
 			pcp->count += rmqueue_bulk(zone, 0,
-					pcp->batch, &pcp->list, migratetype);
+					pcp->batch, &pcp->list,
+					migratetype, cold);
 			page = list_entry(pcp->list.next, struct page, lru);
 		}
 
 		list_del(&page->lru);
 		pcp->count--;
 	} else {
+		if (unlikely(gfp_flags & __GFP_NOFAIL)) {
+			/*
+			 * __GFP_NOFAIL is not to be used in new code.
+			 *
+			 * All __GFP_NOFAIL callers should be fixed so that they
+			 * properly detect and handle allocation failures.
+			 *
+			 * We most definitely don't want callers attempting to
+			 * allocate greater than order-1 page units with
+			 * __GFP_NOFAIL.
+			 */
+			WARN_ON_ONCE(order > 1);
+		}
 		spin_lock_irqsave(&zone->lock, flags);
 		page = __rmqueue(zone, order, migratetype);
+		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
 		spin_unlock(&zone->lock);
 		if (!page)
 			goto failed;
@@ -1123,10 +1187,15 @@ failed:
 	return NULL;
 }
 
-#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
-#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
-#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
-#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
+/* The ALLOC_WMARK bits are used as an index to zone->watermark */
+#define ALLOC_WMARK_MIN		WMARK_MIN
+#define ALLOC_WMARK_LOW		WMARK_LOW
+#define ALLOC_WMARK_HIGH	WMARK_HIGH
+#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */
+
+/* Mask to get the watermark bits */
+#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)
+
 #define ALLOC_HARDER		0x10 /* try to alloc harder */
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
@@ -1384,23 +1453,18 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
  */
 static struct page *
 get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
-		struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
+		struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
+		struct zone *preferred_zone, int migratetype)
 {
 	struct zoneref *z;
 	struct page *page = NULL;
 	int classzone_idx;
-	struct zone *zone, *preferred_zone;
+	struct zone *zone;
 	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 
-	(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
-							&preferred_zone);
-	if (!preferred_zone)
-		return NULL;
-
 	classzone_idx = zone_idx(preferred_zone);
-
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
@@ -1415,31 +1479,49 @@ zonelist_scan:
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				goto try_next_zone;
 
+		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
 			unsigned long mark;
-			if (alloc_flags & ALLOC_WMARK_MIN)
-				mark = zone->pages_min;
-			else if (alloc_flags & ALLOC_WMARK_LOW)
-				mark = zone->pages_low;
-			else
-				mark = zone->pages_high;
-			if (!zone_watermark_ok(zone, order, mark,
-				    classzone_idx, alloc_flags)) {
-				if (!zone_reclaim_mode ||
-				    !zone_reclaim(zone, gfp_mask, order))
+			int ret;
+
+			mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+			if (zone_watermark_ok(zone, order, mark,
+				    classzone_idx, alloc_flags))
+				goto try_this_zone;
+
+			if (zone_reclaim_mode == 0)
+				goto this_zone_full;
+
+			ret = zone_reclaim(zone, gfp_mask, order);
+			switch (ret) {
+			case ZONE_RECLAIM_NOSCAN:
+				/* did not scan */
+				goto try_next_zone;
+			case ZONE_RECLAIM_FULL:
+				/* scanned but unreclaimable */
+				goto this_zone_full;
+			default:
+				/* did we reclaim enough */
+				if (!zone_watermark_ok(zone, order, mark,
+						classzone_idx, alloc_flags))
 					goto this_zone_full;
 			}
 		}
 
-		page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
+try_this_zone:
+		page = buffered_rmqueue(preferred_zone, zone, order,
+						gfp_mask, migratetype);
 		if (page)
 			break;
 this_zone_full:
 		if (NUMA_BUILD)
 			zlc_mark_zone_full(zonelist, z);
 try_next_zone:
-		if (NUMA_BUILD && !did_zlc_setup) {
-			/* we do zlc_setup after the first zone is tried */
+		if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+			/*
+			 * we do zlc_setup after the first zone is tried but only
+			 * if there are multiple nodes make it worthwhile
+			 */
 			allowednodes = zlc_setup(zonelist, alloc_flags);
 			zlc_active = 1;
 			did_zlc_setup = 1;
@@ -1454,47 +1536,219 @@ try_next_zone:
 	return page;
 }
 
+static inline int
+should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+				unsigned long pages_reclaimed)
+{
+	/* Do not loop if specifically requested */
+	if (gfp_mask & __GFP_NORETRY)
+		return 0;
+
+	/*
+	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+	 * means __GFP_NOFAIL, but that may not be true in other
+	 * implementations.
+	 */
+	if (order <= PAGE_ALLOC_COSTLY_ORDER)
+		return 1;
+
+	/*
+	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+	 * specified, then we retry until we no longer reclaim any pages
+	 * (above), or we've reclaimed an order of pages at least as
+	 * large as the allocation's order. In both cases, if the
+	 * allocation still fails, we stop retrying.
+	 */
+	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
+		return 1;
+
+	/*
+	 * Don't let big-order allocations loop unless the caller
+	 * explicitly requests that.
+	 */
+	if (gfp_mask & __GFP_NOFAIL)
+		return 1;
+
+	return 0;
+}
+
+static inline struct page *
+__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, struct zone *preferred_zone,
+	int migratetype)
+{
+	struct page *page;
+
+	/* Acquire the OOM killer lock for the zones in zonelist */
+	if (!try_set_zone_oom(zonelist, gfp_mask)) {
+		schedule_timeout_uninterruptible(1);
+		return NULL;
+	}
+
+	/*
+	 * Go through the zonelist yet one more time, keep very high watermark
+	 * here, this is only to catch a parallel oom killing, we must fail if
+	 * we're still under heavy pressure.
+	 */
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
+		order, zonelist, high_zoneidx,
+		ALLOC_WMARK_HIGH|ALLOC_CPUSET,
+		preferred_zone, migratetype);
+	if (page)
+		goto out;
+
+	/* The OOM killer will not help higher order allocs */
+	if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL))
+		goto out;
+
+	/* Exhausted what can be done so it's blamo time */
+	out_of_memory(zonelist, gfp_mask, order);
+
+out:
+	clear_zonelist_oom(zonelist, gfp_mask);
+	return page;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+static inline struct page *
+__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
+	int migratetype, unsigned long *did_some_progress)
+{
+	struct page *page = NULL;
+	struct reclaim_state reclaim_state;
+	struct task_struct *p = current;
+
+	cond_resched();
+
+	/* We now go into synchronous reclaim */
+	cpuset_memory_pressure_bump();
+
+	/*
+	 * The task's cpuset might have expanded its set of allowable nodes
+	 */
+	p->flags |= PF_MEMALLOC;
+	lockdep_set_current_reclaim_state(gfp_mask);
+	reclaim_state.reclaimed_slab = 0;
+	p->reclaim_state = &reclaim_state;
+
+	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+
+	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+	p->flags &= ~PF_MEMALLOC;
+
+	cond_resched();
+
+	if (order != 0)
+		drain_all_pages();
+
+	if (likely(*did_some_progress))
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
+					zonelist, high_zoneidx,
+					alloc_flags, preferred_zone,
+					migratetype);
+	return page;
+}
+
 /*
- * This is the 'heart' of the zoned buddy allocator.
+ * This is called in the allocator slow-path if the allocation request is of
+ * sufficient urgency to ignore watermarks and take other desperate measures
  */
-struct page *
-__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
-			struct zonelist *zonelist, nodemask_t *nodemask)
+static inline struct page *
+__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, struct zone *preferred_zone,
+	int migratetype)
+{
+	struct page *page;
+
+	do {
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
+			zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
+			preferred_zone, migratetype);
+
+		if (!page && gfp_mask & __GFP_NOFAIL)
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+	} while (!page && (gfp_mask & __GFP_NOFAIL));
+
+	return page;
+}
+
+static inline
+void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
+						enum zone_type high_zoneidx)
 {
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zoneref *z;
 	struct zone *zone;
-	struct page *page;
-	struct reclaim_state reclaim_state;
-	struct task_struct *p = current;
-	int do_retry;
-	int alloc_flags;
-	unsigned long did_some_progress;
-	unsigned long pages_reclaimed = 0;
 
-	lockdep_trace_alloc(gfp_mask);
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		wakeup_kswapd(zone, order);
+}
 
-	might_sleep_if(wait);
+static inline int
+gfp_to_alloc_flags(gfp_t gfp_mask)
+{
+	struct task_struct *p = current;
+	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
+	const gfp_t wait = gfp_mask & __GFP_WAIT;
 
-	if (should_fail_alloc_page(gfp_mask, order))
-		return NULL;
+	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+	BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH);
 
-restart:
-	z = zonelist->_zonerefs;  /* the list of zones suitable for gfp_mask */
+	/*
+	 * The caller may dip into page reserves a bit more if the caller
+	 * cannot run direct reclaim, or if the caller has realtime scheduling
+	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
+	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 */
+	alloc_flags |= (gfp_mask & __GFP_HIGH);
 
-	if (unlikely(!z->zone)) {
+	if (!wait) {
+		alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Happens if we have an empty zonelist as a result of
-		 * GFP_THISNODE being used on a memoryless node
+		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 		 */
-		return NULL;
+		alloc_flags &= ~ALLOC_CPUSET;
+	} else if (unlikely(rt_task(p)))
+		alloc_flags |= ALLOC_HARDER;
+
+	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
+		if (!in_interrupt() &&
+		    ((p->flags & PF_MEMALLOC) ||
+		     unlikely(test_thread_flag(TIF_MEMDIE))))
+			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
-			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
-	if (page)
-		goto got_pg;
+	return alloc_flags;
+}
+
+static inline struct page *
+__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
+	struct zonelist *zonelist, enum zone_type high_zoneidx,
+	nodemask_t *nodemask, struct zone *preferred_zone,
+	int migratetype)
+{
+	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	struct page *page = NULL;
+	int alloc_flags;
+	unsigned long pages_reclaimed = 0;
+	unsigned long did_some_progress;
+	struct task_struct *p = current;
+
+	/*
+	 * In the slowpath, we sanity check order to avoid ever trying to
+	 * reclaim >= MAX_ORDER areas which will never succeed. Callers may
+	 * be using allocators in order of preference for an area that is
+	 * too large.
+	 */
+	if (order >= MAX_ORDER) {
+		WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
+		return NULL;
+	}
 
 	/*
 	 * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
@@ -1507,155 +1761,88 @@ restart:
 	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
-		wakeup_kswapd(zone, order);
+	wake_all_kswapd(order, zonelist, high_zoneidx);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
 	 * reclaim. Now things get more complex, so set up alloc_flags according
 	 * to how we want to proceed.
-	 *
-	 * The caller may dip into page reserves a bit more if the caller
-	 * cannot run direct reclaim, or if the caller has realtime scheduling
-	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
 	 */
-	alloc_flags = ALLOC_WMARK_MIN;
-	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
-		alloc_flags |= ALLOC_HARDER;
-	if (gfp_mask & __GFP_HIGH)
-		alloc_flags |= ALLOC_HIGH;
-	if (wait)
-		alloc_flags |= ALLOC_CPUSET;
+	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
-	/*
-	 * Go through the zonelist again. Let __GFP_HIGH and allocations
-	 * coming from realtime tasks go deeper into reserves.
-	 *
-	 * This is the last chance, in general, before the goto nopage.
-	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
-	 */
+restart:
+	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
-						high_zoneidx, alloc_flags);
+			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
+			preferred_zone, migratetype);
 	if (page)
 		goto got_pg;
 
-	/* This allocation should allow future memory freeing. */
-
 rebalance:
-	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
-			&& !in_interrupt()) {
-		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
-nofail_alloc:
-			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, nodemask, order,
-				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
-			if (page)
-				goto got_pg;
-			if (gfp_mask & __GFP_NOFAIL) {
-				congestion_wait(WRITE, HZ/50);
-				goto nofail_alloc;
-			}
-		}
-		goto nopage;
+	/* Allocate without watermarks if the context allows */
+	if (alloc_flags & ALLOC_NO_WATERMARKS) {
+		page = __alloc_pages_high_priority(gfp_mask, order,
+				zonelist, high_zoneidx, nodemask,
+				preferred_zone, migratetype);
+		if (page)
+			goto got_pg;
 	}
 
 	/* Atomic allocations - we can't balance anything */
 	if (!wait)
 		goto nopage;
 
-	cond_resched();
-
-	/* We now go into synchronous reclaim */
-	cpuset_memory_pressure_bump();
-	/*
-	 * The task's cpuset might have expanded its set of allowable nodes
-	 */
-	cpuset_update_task_memory_state();
-	p->flags |= PF_MEMALLOC;
-
-	lockdep_set_current_reclaim_state(gfp_mask);
-	reclaim_state.reclaimed_slab = 0;
-	p->reclaim_state = &reclaim_state;
+	/* Avoid recursion of direct reclaim */
+	if (p->flags & PF_MEMALLOC)
+		goto nopage;
 
-	did_some_progress = try_to_free_pages(zonelist, order,
-						gfp_mask, nodemask);
+	/* Avoid allocations with no watermarks from looping endlessly */
+	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+		goto nopage;
 
-	p->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
-	p->flags &= ~PF_MEMALLOC;
+	/* Try direct reclaim and then allocating */
+	page = __alloc_pages_direct_reclaim(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask,
+					alloc_flags, preferred_zone,
+					migratetype, &did_some_progress);
+	if (page)
+		goto got_pg;
 
-	cond_resched();
+	/*
+	 * If we failed to make any progress reclaiming, then we are
+	 * running out of options and have to consider going OOM
+	 */
+	if (!did_some_progress) {
+		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+			if (oom_killer_disabled)
+				goto nopage;
+			page = __alloc_pages_may_oom(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask, preferred_zone,
+					migratetype);
+			if (page)
+				goto got_pg;
 
-	if (order != 0)
-		drain_all_pages();
+			/*
+			 * The OOM killer does not trigger for high-order
+			 * ~__GFP_NOFAIL allocations so if no progress is being
+			 * made, there are no other options and retrying is
+			 * unlikely to help.
+			 */
+			if (order > PAGE_ALLOC_COSTLY_ORDER &&
+						!(gfp_mask & __GFP_NOFAIL))
+				goto nopage;
 
-	if (likely(did_some_progress)) {
-		page = get_page_from_freelist(gfp_mask, nodemask, order,
-					zonelist, high_zoneidx, alloc_flags);
-		if (page)
-			goto got_pg;
-	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
-		if (!try_set_zone_oom(zonelist, gfp_mask)) {
-			schedule_timeout_uninterruptible(1);
 			goto restart;
 		}
-
-		/*
-		 * Go through the zonelist yet one more time, keep
-		 * very high watermark here, this is only to catch
-		 * a parallel oom killing, we must fail if we're still
-		 * under heavy pressure.
-		 */
-		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
-			order, zonelist, high_zoneidx,
-			ALLOC_WMARK_HIGH|ALLOC_CPUSET);
-		if (page) {
-			clear_zonelist_oom(zonelist, gfp_mask);
-			goto got_pg;
-		}
-
-		/* The OOM killer will not help higher order allocs so fail */
-		if (order > PAGE_ALLOC_COSTLY_ORDER) {
-			clear_zonelist_oom(zonelist, gfp_mask);
-			goto nopage;
-		}
-
-		out_of_memory(zonelist, gfp_mask, order);
-		clear_zonelist_oom(zonelist, gfp_mask);
-		goto restart;
 	}
 
-	/*
-	 * Don't let big-order allocations loop unless the caller explicitly
-	 * requests that.  Wait for some write requests to complete then retry.
-	 *
-	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
-	 * means __GFP_NOFAIL, but that may not be true in other
-	 * implementations.
-	 *
-	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
-	 * specified, then we retry until we no longer reclaim any pages
-	 * (above), or we've reclaimed an order of pages at least as
-	 * large as the allocation's order. In both cases, if the
-	 * allocation still fails, we stop retrying.
-	 */
+	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
-	do_retry = 0;
-	if (!(gfp_mask & __GFP_NORETRY)) {
-		if (order <= PAGE_ALLOC_COSTLY_ORDER) {
-			do_retry = 1;
-		} else {
-			if (gfp_mask & __GFP_REPEAT &&
-				pages_reclaimed < (1 << order))
-					do_retry = 1;
-		}
-		if (gfp_mask & __GFP_NOFAIL)
-			do_retry = 1;
-	}
-	if (do_retry) {
-		congestion_wait(WRITE, HZ/50);
+	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+		/* Wait for some write requests to complete then retry */
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
 	}
 
@@ -1667,10 +1854,60 @@ nopage:
 		dump_stack();
 		show_mem();
 	}
+	return page;
 got_pg:
+	if (kmemcheck_enabled)
+		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
+	return page;
+
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+			struct zonelist *zonelist, nodemask_t *nodemask)
+{
+	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+	struct zone *preferred_zone;
+	struct page *page;
+	int migratetype = allocflags_to_migratetype(gfp_mask);
+
+	gfp_mask &= gfp_allowed_mask;
+
+	lockdep_trace_alloc(gfp_mask);
+
+	might_sleep_if(gfp_mask & __GFP_WAIT);
+
+	if (should_fail_alloc_page(gfp_mask, order))
+		return NULL;
+
+	/*
+	 * Check the zones suitable for the gfp_mask contain at least one
+	 * valid zone. It's possible to have an empty zonelist as a result
+	 * of GFP_THISNODE and a memoryless node
+	 */
+	if (unlikely(!zonelist->_zonerefs->zone))
+		return NULL;
+
+	/* The preferred zone is used for statistics later */
+	first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+	if (!preferred_zone)
+		return NULL;
+
+	/* First allocation attempt */
+	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+			zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET,
+			preferred_zone, migratetype);
+	if (unlikely(!page))
+		page = __alloc_pages_slowpath(gfp_mask, order,
+				zonelist, high_zoneidx, nodemask,
+				preferred_zone, migratetype);
+
 	return page;
 }
-EXPORT_SYMBOL(__alloc_pages_internal);
+EXPORT_SYMBOL(__alloc_pages_nodemask);
 
 /*
  * Common helper functions.
@@ -1757,7 +1994,7 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
 		unsigned long alloc_end = addr + (PAGE_SIZE << order);
 		unsigned long used = addr + PAGE_ALIGN(size);
 
-		split_page(virt_to_page(addr), order);
+		split_page(virt_to_page((void *)addr), order);
 		while (used < alloc_end) {
 			free_page(used);
 			used += PAGE_SIZE;
@@ -1799,7 +2036,7 @@ static unsigned int nr_free_zone_pages(int offset)
 
 	for_each_zone_zonelist(zone, z, zonelist, offset) {
 		unsigned long size = zone->present_pages;
-		unsigned long high = zone->pages_high;
+		unsigned long high = high_wmark_pages(zone);
 		if (size > high)
 			sum += size - high;
 	}
@@ -1891,19 +2128,14 @@ void show_free_areas(void)
 
 	printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n"
 		" inactive_file:%lu"
-//TODO:  check/adjust line lengths
-#ifdef CONFIG_UNEVICTABLE_LRU
 		" unevictable:%lu"
-#endif
 		" dirty:%lu writeback:%lu unstable:%lu\n"
 		" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
 		global_page_state(NR_ACTIVE_ANON),
 		global_page_state(NR_ACTIVE_FILE),
 		global_page_state(NR_INACTIVE_ANON),
 		global_page_state(NR_INACTIVE_FILE),
-#ifdef CONFIG_UNEVICTABLE_LRU
 		global_page_state(NR_UNEVICTABLE),
-#endif
 		global_page_state(NR_FILE_DIRTY),
 		global_page_state(NR_WRITEBACK),
 		global_page_state(NR_UNSTABLE_NFS),
@@ -1927,25 +2159,21 @@ void show_free_areas(void)
 			" inactive_anon:%lukB"
 			" active_file:%lukB"
 			" inactive_file:%lukB"
-#ifdef CONFIG_UNEVICTABLE_LRU
 			" unevictable:%lukB"
-#endif
 			" present:%lukB"
 			" pages_scanned:%lu"
 			" all_unreclaimable? %s"
 			"\n",
 			zone->name,
 			K(zone_page_state(zone, NR_FREE_PAGES)),
-			K(zone->pages_min),
-			K(zone->pages_low),
-			K(zone->pages_high),
+			K(min_wmark_pages(zone)),
+			K(low_wmark_pages(zone)),
+			K(high_wmark_pages(zone)),
 			K(zone_page_state(zone, NR_ACTIVE_ANON)),
 			K(zone_page_state(zone, NR_INACTIVE_ANON)),
 			K(zone_page_state(zone, NR_ACTIVE_FILE)),
 			K(zone_page_state(zone, NR_INACTIVE_FILE)),
-#ifdef CONFIG_UNEVICTABLE_LRU
 			K(zone_page_state(zone, NR_UNEVICTABLE)),
-#endif
 			K(zone->present_pages),
 			zone->pages_scanned,
 			(zone_is_all_unreclaimable(zone) ? "yes" : "no")
@@ -2103,7 +2331,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 }
 
 
-#define MAX_NODE_LOAD (num_online_nodes())
+#define MAX_NODE_LOAD (nr_online_nodes)
 static int node_load[MAX_NUMNODES];
 
 /**
@@ -2312,11 +2540,10 @@ static void build_zonelists(pg_data_t *pgdat)
 
 	/* NUMA-aware ordering of nodes */
 	local_node = pgdat->node_id;
-	load = num_online_nodes();
+	load = nr_online_nodes;
 	prev_node = local_node;
 	nodes_clear(used_mask);
 
-	memset(node_load, 0, sizeof(node_load));
 	memset(node_order, 0, sizeof(node_order));
 	j = 0;
 
@@ -2425,6 +2652,9 @@ static int __build_all_zonelists(void *dummy)
 {
 	int nid;
 
+#ifdef CONFIG_NUMA
+	memset(node_load, 0, sizeof(node_load));
+#endif
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 
@@ -2463,7 +2693,7 @@ void build_all_zonelists(void)
 
 	printk("Built %i zonelists in %s order, mobility grouping %s.  "
 		"Total pages: %ld\n",
-			num_online_nodes(),
+			nr_online_nodes,
 			zonelist_order_name[current_zonelist_order],
 			page_group_by_mobility_disabled ? "off" : "on",
 			vm_total_pages);
@@ -2542,8 +2772,8 @@ static inline unsigned long wait_table_bits(unsigned long size)
 
 /*
  * Mark a number of pageblocks as MIGRATE_RESERVE. The number
- * of blocks reserved is based on zone->pages_min. The memory within the
- * reserve will tend to store contiguous free pages. Setting min_free_kbytes
+ * of blocks reserved is based on min_wmark_pages(zone). The memory within
+ * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
  * higher will lead to a bigger reserve which will get freed as contiguous
  * blocks as reclaim kicks in
  */
@@ -2556,7 +2786,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	/* Get the start pfn, end pfn and the number of blocks to reserve */
 	start_pfn = zone->zone_start_pfn;
 	end_pfn = start_pfn + zone->spanned_pages;
-	reserve = roundup(zone->pages_min, pageblock_nr_pages) >>
+	reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
 							pageblock_order;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
@@ -2809,7 +3039,7 @@ bad:
 		if (dzone == zone)
 			break;
 		kfree(zone_pcp(dzone, cpu));
-		zone_pcp(dzone, cpu) = NULL;
+		zone_pcp(dzone, cpu) = &boot_pageset[cpu];
 	}
 	return -ENOMEM;
 }
@@ -2824,7 +3054,7 @@ static inline void free_zone_pagesets(int cpu)
 		/* Free per_cpu_pageset if it is slab allocated */
 		if (pset != &boot_pageset[cpu])
 			kfree(pset);
-		zone_pcp(zone, cpu) = NULL;
+		zone_pcp(zone, cpu) = &boot_pageset[cpu];
 	}
 }
 
@@ -3488,7 +3718,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone_pcp_init(zone);
 		for_each_lru(l) {
 			INIT_LIST_HEAD(&zone->lru[l].list);
-			zone->lru[l].nr_scan = 0;
+			zone->lru[l].nr_saved_scan = 0;
 		}
 		zone->reclaim_stat.recent_rotated[0] = 0;
 		zone->reclaim_stat.recent_rotated[1] = 0;
@@ -3815,6 +4045,8 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
 	int i, nid;
 	unsigned long usable_startpfn;
 	unsigned long kernelcore_node, kernelcore_remaining;
+	/* save the state before borrow the nodemask */
+	nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
 	unsigned long totalpages = early_calculate_totalpages();
 	int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
 
@@ -3842,7 +4074,7 @@ static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
 
 	/* If kernelcore was not specified, there is no ZONE_MOVABLE */
 	if (!required_kernelcore)
-		return;
+		goto out;
 
 	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
 	find_usable_zone_for_movable();
@@ -3941,6 +4173,10 @@ restart:
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
 		zone_movable_pfn[nid] =
 			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
+
+out:
+	/* restore the node_state */
+	node_states[N_HIGH_MEMORY] = saved_node_state;
 }
 
 /* Any regular memory on that node ? */
@@ -4159,8 +4395,8 @@ static void calculate_totalreserve_pages(void)
 					max = zone->lowmem_reserve[j];
 			}
 
-			/* we treat pages_high as reserved pages. */
-			max += zone->pages_high;
+			/* we treat the high watermark as reserved pages. */
+			max += high_wmark_pages(zone);
 
 			if (max > zone->present_pages)
 				max = zone->present_pages;
@@ -4210,12 +4446,13 @@ static void setup_per_zone_lowmem_reserve(void)
 }
 
 /**
- * setup_per_zone_pages_min - called when min_free_kbytes changes.
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
  *
- * Ensures that the pages_{min,low,high} values for each zone are set correctly
- * with respect to min_free_kbytes.
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
  */
-void setup_per_zone_pages_min(void)
+void setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
@@ -4240,7 +4477,7 @@ void setup_per_zone_pages_min(void)
 			 * need highmem pages, so cap pages_min to a small
 			 * value here.
 			 *
-			 * The (pages_high-pages_low) and (pages_low-pages_min)
+			 * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
 			 * deltas controls asynch page reclaim, and so should
 			 * not be capped for highmem.
 			 */
@@ -4251,17 +4488,17 @@ void setup_per_zone_pages_min(void)
 				min_pages = SWAP_CLUSTER_MAX;
 			if (min_pages > 128)
 				min_pages = 128;
-			zone->pages_min = min_pages;
+			zone->watermark[WMARK_MIN] = min_pages;
 		} else {
 			/*
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
-			zone->pages_min = tmp;
+			zone->watermark[WMARK_MIN] = tmp;
 		}
 
-		zone->pages_low   = zone->pages_min + (tmp >> 2);
-		zone->pages_high  = zone->pages_min + (tmp >> 1);
+		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
+		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
@@ -4271,8 +4508,6 @@ void setup_per_zone_pages_min(void)
 }
 
 /**
- * setup_per_zone_inactive_ratio - called when min_free_kbytes changes.
- *
  * The inactive anon list should be small enough that the VM never has to
  * do too much work, but large enough that each inactive page has a chance
  * to be referenced again before it is swapped out.
@@ -4293,21 +4528,26 @@ void setup_per_zone_pages_min(void)
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-static void setup_per_zone_inactive_ratio(void)
+void calculate_zone_inactive_ratio(struct zone *zone)
 {
-	struct zone *zone;
+	unsigned int gb, ratio;
 
-	for_each_zone(zone) {
-		unsigned int gb, ratio;
-
-		/* Zone size in gigabytes */
-		gb = zone->present_pages >> (30 - PAGE_SHIFT);
+	/* Zone size in gigabytes */
+	gb = zone->present_pages >> (30 - PAGE_SHIFT);
+	if (gb)
 		ratio = int_sqrt(10 * gb);
-		if (!ratio)
-			ratio = 1;
+	else
+		ratio = 1;
 
-		zone->inactive_ratio = ratio;
-	}
+	zone->inactive_ratio = ratio;
+}
+
+static void __init setup_per_zone_inactive_ratio(void)
+{
+	struct zone *zone;
+
+	for_each_zone(zone)
+		calculate_zone_inactive_ratio(zone);
 }
 
 /*
@@ -4334,7 +4574,7 @@ static void setup_per_zone_inactive_ratio(void)
  * 8192MB:	11584k
  * 16384MB:	16384k
  */
-static int __init init_per_zone_pages_min(void)
+static int __init init_per_zone_wmark_min(void)
 {
 	unsigned long lowmem_kbytes;
 
@@ -4345,12 +4585,12 @@ static int __init init_per_zone_pages_min(void)
 		min_free_kbytes = 128;
 	if (min_free_kbytes > 65536)
 		min_free_kbytes = 65536;
-	setup_per_zone_pages_min();
+	setup_per_zone_wmarks();
 	setup_per_zone_lowmem_reserve();
 	setup_per_zone_inactive_ratio();
 	return 0;
 }
-module_init(init_per_zone_pages_min)
+module_init(init_per_zone_wmark_min)
 
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
@@ -4362,7 +4602,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 {
 	proc_dointvec(table, write, file, buffer, length, ppos);
 	if (write)
-		setup_per_zone_pages_min();
+		setup_per_zone_wmarks();
 	return 0;
 }
 
@@ -4406,7 +4646,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
  *	whenever sysctl_lowmem_reserve_ratio changes.
  *
  * The reserve ratio obviously has absolutely no relation with the
- * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * minimum watermarks. The lowmem reserve ratio can only make sense
  * if in function of the boot time zone sizes.
  */
 int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
@@ -4433,7 +4673,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
 	if (!write || (ret == -EINVAL))
 		return ret;
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		for_each_online_cpu(cpu) {
 			unsigned long  high;
 			high = zone->present_pages / percpu_pagelist_fraction;
@@ -4513,22 +4753,14 @@ void *__init alloc_large_system_hash(const char *tablename,
 		else if (hashdist)
 			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
 		else {
-			unsigned long order = get_order(size);
-			table = (void*) __get_free_pages(GFP_ATOMIC, order);
 			/*
 			 * If bucketsize is not a power-of-two, we may free
-			 * some pages at the end of hash table.
+			 * some pages at the end of hash table which
+			 * alloc_pages_exact() automatically does
 			 */
-			if (table) {
-				unsigned long alloc_end = (unsigned long)table +
-						(PAGE_SIZE << order);
-				unsigned long used = (unsigned long)table +
-						PAGE_ALIGN(size);
-				split_page(virt_to_page(table), order);
-				while (used < alloc_end) {
-					free_page(used);
-					used += PAGE_SIZE;
-				}
+			if (get_order(size) < MAX_ORDER) {
+				table = alloc_pages_exact(size, GFP_ATOMIC);
+				kmemleak_alloc(table, size, 1, GFP_ATOMIC);
 			}
 		}
 	} while (!table && size > PAGE_SIZE && --log2qty);
@@ -4547,16 +4779,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (_hash_mask)
 		*_hash_mask = (1 << log2qty) - 1;
 
-	/*
-	 * If hashdist is set, the table allocation is done with __vmalloc()
-	 * which invokes the kmemleak_alloc() callback. This function may also
-	 * be called before the slab and kmemleak are initialised when
-	 * kmemleak simply buffers the request to be executed later
-	 * (GFP_ATOMIC flag ignored in this case).
-	 */
-	if (!hashdist)
-		kmemleak_alloc(table, size, 1, GFP_ATOMIC);
-
 	return table;
 }
 
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 11a8a10a3909..f22b4ebbd8dc 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -83,12 +83,12 @@ void __init page_cgroup_init_flatmem(void)
 			goto fail;
 	}
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try cgroup_disable=memory option if you"
-	" don't want\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
+	" don't want memory cgroups\n");
 	return;
 fail:
-	printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
-	printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
+	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
 	panic("Out of memory");
 }
 
@@ -99,6 +99,8 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
 	unsigned long pfn = page_to_pfn(page);
 	struct mem_section *section = __pfn_to_section(pfn);
 
+	if (!section->page_cgroup)
+		return NULL;
 	return section->page_cgroup + pfn;
 }
 
@@ -252,14 +254,14 @@ void __init page_cgroup_init(void)
 		fail = init_section_page_cgroup(pfn);
 	}
 	if (fail) {
-		printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+		printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
 		panic("Out of memory");
 	} else {
 		hotplug_memory_notifier(page_cgroup_callback, 0);
 	}
 	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try cgroup_disable=memory option if you don't"
-	" want\n");
+	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
+	" want memory cgroups\n");
 }
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
@@ -309,8 +311,6 @@ static int swap_cgroup_prepare(int type)
 	struct swap_cgroup_ctrl *ctrl;
 	unsigned long idx, max;
 
-	if (!do_swap_account)
-		return 0;
 	ctrl = &swap_cgroup_ctrl[type];
 
 	for (idx = 0; idx < ctrl->length; idx++) {
@@ -347,9 +347,6 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 	struct swap_cgroup *sc;
 	unsigned short old;
 
-	if (!do_swap_account)
-		return 0;
-
 	ctrl = &swap_cgroup_ctrl[type];
 
 	mappage = ctrl->map[idx];
@@ -378,9 +375,6 @@ unsigned short lookup_swap_cgroup(swp_entry_t ent)
 	struct swap_cgroup *sc;
 	unsigned short ret;
 
-	if (!do_swap_account)
-		return 0;
-
 	ctrl = &swap_cgroup_ctrl[type];
 	mappage = ctrl->map[idx];
 	sc = page_address(mappage);
diff --git a/mm/page_io.c b/mm/page_io.c
index 3023c475e041..c6f3e5071de3 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -120,7 +120,7 @@ out:
 	return ret;
 }
 
-int swap_readpage(struct file *file, struct page *page)
+int swap_readpage(struct page *page)
 {
 	struct bio *bio;
 	int ret = 0;
diff --git a/mm/percpu.c b/mm/percpu.c
index c0b2c1a76e81..5fe37842e0ea 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -8,12 +8,12 @@
  *
  * This is percpu allocator which can handle both static and dynamic
  * areas.  Percpu areas are allocated in chunks in vmalloc area.  Each
- * chunk is consisted of num_possible_cpus() units and the first chunk
- * is used for static percpu variables in the kernel image (special
- * boot time alloc/init handling necessary as these areas need to be
- * brought up before allocation services are running).  Unit grows as
- * necessary and all units grow or shrink in unison.  When a chunk is
- * filled up, another chunk is allocated.  ie. in vmalloc area
+ * chunk is consisted of nr_cpu_ids units and the first chunk is used
+ * for static percpu variables in the kernel image (special boot time
+ * alloc/init handling necessary as these areas need to be brought up
+ * before allocation services are running).  Unit grows as necessary
+ * and all units grow or shrink in unison.  When a chunk is filled up,
+ * another chunk is allocated.  ie. in vmalloc area
  *
  *  c0                           c1                         c2
  *  -------------------          -------------------        ------------
@@ -549,16 +549,16 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
  * @chunk: chunk of interest
  * @page_start: page index of the first page to unmap
  * @page_end: page index of the last page to unmap + 1
- * @flush: whether to flush cache and tlb or not
+ * @flush_tlb: whether to flush tlb or not
  *
  * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
  * If @flush is true, vcache is flushed before unmapping and tlb
  * after.
  */
 static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
-		       bool flush)
+		       bool flush_tlb)
 {
-	unsigned int last = num_possible_cpus() - 1;
+	unsigned int last = nr_cpu_ids - 1;
 	unsigned int cpu;
 
 	/* unmap must not be done on immutable chunk */
@@ -569,9 +569,8 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
 	 * the whole region at once rather than doing it for each cpu.
 	 * This could be an overkill but is more scalable.
 	 */
-	if (flush)
-		flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
-				   pcpu_chunk_addr(chunk, last, page_end));
+	flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
+			   pcpu_chunk_addr(chunk, last, page_end));
 
 	for_each_possible_cpu(cpu)
 		unmap_kernel_range_noflush(
@@ -579,7 +578,7 @@ static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
 				(page_end - page_start) << PAGE_SHIFT);
 
 	/* ditto as flush_cache_vunmap() */
-	if (flush)
+	if (flush_tlb)
 		flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start),
 				       pcpu_chunk_addr(chunk, last, page_end));
 }
@@ -644,7 +643,7 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size,
  */
 static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end)
 {
-	unsigned int last = num_possible_cpus() - 1;
+	unsigned int last = nr_cpu_ids - 1;
 	unsigned int cpu;
 	int err;
 
@@ -750,7 +749,7 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
 	chunk->map[chunk->map_used++] = pcpu_unit_size;
 	chunk->page = chunk->page_ar;
 
-	chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL);
+	chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC);
 	if (!chunk->vm) {
 		free_pcpu_chunk(chunk);
 		return NULL;
@@ -1068,9 +1067,9 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 					PFN_UP(size_sum));
 
 	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
-	pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
+	pcpu_chunk_size = nr_cpu_ids * pcpu_unit_size;
 	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk)
-		+ num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *);
+		+ nr_cpu_ids * pcpu_unit_pages * sizeof(struct page *);
 
 	if (dyn_size < 0)
 		dyn_size = pcpu_unit_size - static_size - reserved_size;
@@ -1234,6 +1233,7 @@ static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
 ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
 				      ssize_t dyn_size, ssize_t unit_size)
 {
+	size_t chunk_size;
 	unsigned int cpu;
 
 	/* determine parameters and allocate */
@@ -1248,19 +1248,26 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
 	} else
 		pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
 
-	pcpue_ptr = __alloc_bootmem_nopanic(
-					num_possible_cpus() * pcpue_unit_size,
-					PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
-	if (!pcpue_ptr)
+	chunk_size = pcpue_unit_size * nr_cpu_ids;
+
+	pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE,
+					    __pa(MAX_DMA_ADDRESS));
+	if (!pcpue_ptr) {
+		pr_warning("PERCPU: failed to allocate %zu bytes for "
+			   "embedding\n", chunk_size);
 		return -ENOMEM;
+	}
 
 	/* return the leftover and copy */
-	for_each_possible_cpu(cpu) {
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
 		void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
 
-		free_bootmem(__pa(ptr + pcpue_size),
-			     pcpue_unit_size - pcpue_size);
-		memcpy(ptr, __per_cpu_load, static_size);
+		if (cpu_possible(cpu)) {
+			free_bootmem(__pa(ptr + pcpue_size),
+				     pcpue_unit_size - pcpue_size);
+			memcpy(ptr, __per_cpu_load, static_size);
+		} else
+			free_bootmem(__pa(ptr), pcpue_unit_size);
 	}
 
 	/* we're ready, commit */
diff --git a/mm/readahead.c b/mm/readahead.c
index 133b6d525513..aa1aa2345235 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -133,15 +133,12 @@ out:
 }
 
 /*
- * do_page_cache_readahead actually reads a chunk of disk.  It allocates all
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
  * the pages first, then submits them all for I/O. This avoids the very bad
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
- *
- * do_page_cache_readahead() returns -1 if it encountered request queue
- * congestion.
  */
 static int
 __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
@@ -210,6 +207,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
 		return -EINVAL;
 
+	nr_to_read = max_sane_readahead(nr_to_read);
 	while (nr_to_read) {
 		int err;
 
@@ -231,22 +229,6 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 }
 
 /*
- * This version skips the IO if the queue is read-congested, and will tell the
- * block layer to abandon the readahead if request allocation would block.
- *
- * force_page_cache_readahead() will ignore queue congestion and will block on
- * request queues.
- */
-int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
-			pgoff_t offset, unsigned long nr_to_read)
-{
-	if (bdi_read_congested(mapping->backing_dev_info))
-		return -1;
-
-	return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
-}
-
-/*
  * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
  * sensible upper limit.
  */
@@ -259,7 +241,7 @@ unsigned long max_sane_readahead(unsigned long nr)
 /*
  * Submit IO for the read-ahead request in file_ra_state.
  */
-static unsigned long ra_submit(struct file_ra_state *ra,
+unsigned long ra_submit(struct file_ra_state *ra,
 		       struct address_space *mapping, struct file *filp)
 {
 	int actual;
@@ -348,6 +330,59 @@ static unsigned long get_next_ra_size(struct file_ra_state *ra,
  */
 
 /*
+ * Count contiguously cached pages from @offset-1 to @offset-@max,
+ * this count is a conservative estimation of
+ * 	- length of the sequential read sequence, or
+ * 	- thrashing threshold in memory tight systems
+ */
+static pgoff_t count_history_pages(struct address_space *mapping,
+				   struct file_ra_state *ra,
+				   pgoff_t offset, unsigned long max)
+{
+	pgoff_t head;
+
+	rcu_read_lock();
+	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	rcu_read_unlock();
+
+	return offset - 1 - head;
+}
+
+/*
+ * page cache context based read-ahead
+ */
+static int try_context_readahead(struct address_space *mapping,
+				 struct file_ra_state *ra,
+				 pgoff_t offset,
+				 unsigned long req_size,
+				 unsigned long max)
+{
+	pgoff_t size;
+
+	size = count_history_pages(mapping, ra, offset, max);
+
+	/*
+	 * no history pages:
+	 * it could be a random read
+	 */
+	if (!size)
+		return 0;
+
+	/*
+	 * starts from beginning of file:
+	 * it is a strong indication of long-run stream (or whole-file-read)
+	 */
+	if (size >= offset)
+		size *= 2;
+
+	ra->start = offset;
+	ra->size = get_init_ra_size(size + req_size, max);
+	ra->async_size = ra->size;
+
+	return 1;
+}
+
+/*
  * A minimal readahead algorithm for trivial sequential/random reads.
  */
 static unsigned long
@@ -356,34 +391,26 @@ ondemand_readahead(struct address_space *mapping,
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	int	max = ra->ra_pages;	/* max readahead pages */
-	pgoff_t prev_offset;
-	int	sequential;
+	unsigned long max = max_sane_readahead(ra->ra_pages);
+
+	/*
+	 * start of file
+	 */
+	if (!offset)
+		goto initial_readahead;
 
 	/*
 	 * It's the expected callback offset, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	if (offset && (offset == (ra->start + ra->size - ra->async_size) ||
-			offset == (ra->start + ra->size))) {
+	if ((offset == (ra->start + ra->size - ra->async_size) ||
+	     offset == (ra->start + ra->size))) {
 		ra->start += ra->size;
 		ra->size = get_next_ra_size(ra, max);
 		ra->async_size = ra->size;
 		goto readit;
 	}
 
-	prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT;
-	sequential = offset - prev_offset <= 1UL || req_size > max;
-
-	/*
-	 * Standalone, small read.
-	 * Read as is, and do not pollute the readahead state.
-	 */
-	if (!hit_readahead_marker && !sequential) {
-		return __do_page_cache_readahead(mapping, filp,
-						offset, req_size, 0);
-	}
-
 	/*
 	 * Hit a marked page without valid readahead state.
 	 * E.g. interleaved reads.
@@ -394,7 +421,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset,max+1);
+		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
@@ -402,23 +429,53 @@ ondemand_readahead(struct address_space *mapping,
 
 		ra->start = start;
 		ra->size = start - offset;	/* old async_size */
+		ra->size += req_size;
 		ra->size = get_next_ra_size(ra, max);
 		ra->async_size = ra->size;
 		goto readit;
 	}
 
 	/*
-	 * It may be one of
-	 * 	- first read on start of file
-	 * 	- sequential cache miss
-	 * 	- oversize random read
-	 * Start readahead for it.
+	 * oversize read
+	 */
+	if (req_size > max)
+		goto initial_readahead;
+
+	/*
+	 * sequential cache miss
+	 */
+	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+		goto initial_readahead;
+
+	/*
+	 * Query the page cache and look for the traces(cached history pages)
+	 * that a sequential stream would leave behind.
+	 */
+	if (try_context_readahead(mapping, ra, offset, req_size, max))
+		goto readit;
+
+	/*
+	 * standalone, small random read
+	 * Read as is, and do not pollute the readahead state.
 	 */
+	return __do_page_cache_readahead(mapping, filp, offset, req_size, 0);
+
+initial_readahead:
 	ra->start = offset;
 	ra->size = get_init_ra_size(req_size, max);
 	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
 
 readit:
+	/*
+	 * Will this read hit the readahead marker made by itself?
+	 * If so, trigger the readahead marker hit now, and merge
+	 * the resulted next readahead window into the current one.
+	 */
+	if (offset == ra->start && ra->size == ra->async_size) {
+		ra->async_size = get_next_ra_size(ra, max);
+		ra->size += ra->async_size;
+	}
+
 	return ra_submit(ra, mapping, filp);
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 23122af32611..836c6c63e1f2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -333,7 +333,9 @@ static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
  * repeatedly from either page_referenced_anon or page_referenced_file.
  */
 static int page_referenced_one(struct page *page,
-	struct vm_area_struct *vma, unsigned int *mapcount)
+			       struct vm_area_struct *vma,
+			       unsigned int *mapcount,
+			       unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -381,11 +383,14 @@ out_unmap:
 	(*mapcount)--;
 	pte_unmap_unlock(pte, ptl);
 out:
+	if (referenced)
+		*vm_flags |= vma->vm_flags;
 	return referenced;
 }
 
 static int page_referenced_anon(struct page *page,
-				struct mem_cgroup *mem_cont)
+				struct mem_cgroup *mem_cont,
+				unsigned long *vm_flags)
 {
 	unsigned int mapcount;
 	struct anon_vma *anon_vma;
@@ -405,7 +410,8 @@ static int page_referenced_anon(struct page *page,
 		 */
 		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
 			continue;
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma,
+						  &mapcount, vm_flags);
 		if (!mapcount)
 			break;
 	}
@@ -418,6 +424,7 @@ static int page_referenced_anon(struct page *page,
  * page_referenced_file - referenced check for object-based rmap
  * @page: the page we're checking references on.
  * @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
  *
  * For an object-based mapped page, find all the places it is mapped and
  * check/clear the referenced flag.  This is done by following the page->mapping
@@ -427,7 +434,8 @@ static int page_referenced_anon(struct page *page,
  * This function is only called from page_referenced for object-based pages.
  */
 static int page_referenced_file(struct page *page,
-				struct mem_cgroup *mem_cont)
+				struct mem_cgroup *mem_cont,
+				unsigned long *vm_flags)
 {
 	unsigned int mapcount;
 	struct address_space *mapping = page->mapping;
@@ -467,7 +475,8 @@ static int page_referenced_file(struct page *page,
 		 */
 		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
 			continue;
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma,
+						  &mapcount, vm_flags);
 		if (!mapcount)
 			break;
 	}
@@ -481,29 +490,35 @@ static int page_referenced_file(struct page *page,
  * @page: the page to test
  * @is_locked: caller holds lock on the page
  * @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
  *
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
  */
-int page_referenced(struct page *page, int is_locked,
-			struct mem_cgroup *mem_cont)
+int page_referenced(struct page *page,
+		    int is_locked,
+		    struct mem_cgroup *mem_cont,
+		    unsigned long *vm_flags)
 {
 	int referenced = 0;
 
 	if (TestClearPageReferenced(page))
 		referenced++;
 
+	*vm_flags = 0;
 	if (page_mapped(page) && page->mapping) {
 		if (PageAnon(page))
-			referenced += page_referenced_anon(page, mem_cont);
+			referenced += page_referenced_anon(page, mem_cont,
+								vm_flags);
 		else if (is_locked)
-			referenced += page_referenced_file(page, mem_cont);
+			referenced += page_referenced_file(page, mem_cont,
+								vm_flags);
 		else if (!trylock_page(page))
 			referenced++;
 		else {
 			if (page->mapping)
-				referenced +=
-					page_referenced_file(page, mem_cont);
+				referenced += page_referenced_file(page,
+							mem_cont, vm_flags);
 			unlock_page(page);
 		}
 	}
@@ -688,8 +703,10 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
-	if (atomic_inc_and_test(&page->_mapcount))
+	if (atomic_inc_and_test(&page->_mapcount)) {
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
+		mem_cgroup_update_mapped_file_stat(page, 1);
+	}
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -738,6 +755,7 @@ void page_remove_rmap(struct page *page)
 			mem_cgroup_uncharge_page(page);
 		__dec_zone_page_state(page,
 			PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
+		mem_cgroup_update_mapped_file_stat(page, -1);
 		/*
 		 * It would be tidy to reset the PageAnon mapping here,
 		 * but that might overwrite a racing page_add_anon_rmap
@@ -1202,7 +1220,6 @@ int try_to_unmap(struct page *page, int migration)
 	return ret;
 }
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /**
  * try_to_munlock - try to munlock a page
  * @page: the page to be munlocked
@@ -1226,4 +1243,4 @@ int try_to_munlock(struct page *page)
 	else
 		return try_to_unmap_file(page, 1, 0);
 }
-#endif
+
diff --git a/mm/shmem.c b/mm/shmem.c
index 0132fbd45a23..d713239ce2ce 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1097,7 +1097,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	shmem_swp_unmap(entry);
 unlock:
 	spin_unlock(&info->lock);
-	swap_free(swap);
+	swapcache_free(swap, NULL);
 redirty:
 	set_page_dirty(page);
 	if (wbc->for_reclaim)
@@ -1558,6 +1558,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, int mode,
 		spin_lock_init(&info->lock);
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
+		cache_no_acl(inode);
 
 		switch (mode & S_IFMT) {
 		default:
@@ -2388,7 +2389,6 @@ static void shmem_destroy_inode(struct inode *inode)
 		/* only struct inode is valid if it's an inline symlink */
 		mpol_free_shared_policy(&SHMEM_I(inode)->policy);
 	}
-	shmem_acl_destroy_inode(inode);
 	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
 }
 
@@ -2397,10 +2397,6 @@ static void init_once(void *foo)
 	struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
 
 	inode_init_once(&p->vfs_inode);
-#ifdef CONFIG_TMPFS_POSIX_ACL
-	p->i_acl = NULL;
-	p->i_default_acl = NULL;
-#endif
 }
 
 static int init_inodecache(void)
@@ -2612,7 +2608,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
  * @size: size to be set for the file
  * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
  */
-struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
 {
 	int error;
 	struct file *file;
diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c
index 8e5aadd7dcd6..606a8e757a42 100644
--- a/mm/shmem_acl.c
+++ b/mm/shmem_acl.c
@@ -22,11 +22,11 @@ shmem_get_acl(struct inode *inode, int type)
 	spin_lock(&inode->i_lock);
 	switch(type) {
 		case ACL_TYPE_ACCESS:
-			acl = posix_acl_dup(SHMEM_I(inode)->i_acl);
+			acl = posix_acl_dup(inode->i_acl);
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			acl = posix_acl_dup(SHMEM_I(inode)->i_default_acl);
+			acl = posix_acl_dup(inode->i_default_acl);
 			break;
 	}
 	spin_unlock(&inode->i_lock);
@@ -45,13 +45,13 @@ shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 	spin_lock(&inode->i_lock);
 	switch(type) {
 		case ACL_TYPE_ACCESS:
-			free = SHMEM_I(inode)->i_acl;
-			SHMEM_I(inode)->i_acl = posix_acl_dup(acl);
+			free = inode->i_acl;
+			inode->i_acl = posix_acl_dup(acl);
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			free = SHMEM_I(inode)->i_default_acl;
-			SHMEM_I(inode)->i_default_acl = posix_acl_dup(acl);
+			free = inode->i_default_acl;
+			inode->i_default_acl = posix_acl_dup(acl);
 			break;
 	}
 	spin_unlock(&inode->i_lock);
@@ -155,23 +155,6 @@ shmem_acl_init(struct inode *inode, struct inode *dir)
 }
 
 /**
- * shmem_acl_destroy_inode  -  destroy acls hanging off the in-memory inode
- *
- * This is done before destroying the actual inode.
- */
-
-void
-shmem_acl_destroy_inode(struct inode *inode)
-{
-	if (SHMEM_I(inode)->i_acl)
-		posix_acl_release(SHMEM_I(inode)->i_acl);
-	SHMEM_I(inode)->i_acl = NULL;
-	if (SHMEM_I(inode)->i_default_acl)
-		posix_acl_release(SHMEM_I(inode)->i_default_acl);
-	SHMEM_I(inode)->i_default_acl = NULL;
-}
-
-/**
  * shmem_check_acl  -  check_acl() callback for generic_permission()
  */
 static int
diff --git a/mm/slab.c b/mm/slab.c
index 18e3164de09a..7b5d4deacfcd 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -114,6 +114,7 @@
 #include	<linux/rtmutex.h>
 #include	<linux/reciprocal_div.h>
 #include	<linux/debugobjects.h>
+#include	<linux/kmemcheck.h>
 
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
@@ -179,13 +180,13 @@
 			 SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
 #else
 # define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
 			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
-			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE)
+			 SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE | SLAB_NOTRACK)
 #endif
 
 /*
@@ -304,12 +305,6 @@ struct kmem_list3 {
 };
 
 /*
- * The slab allocator is initialized with interrupts disabled. Therefore, make
- * sure early boot allocations don't accidentally enable interrupts.
- */
-static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK;
-
-/*
  * Need this for bootstrapping a per node allocator.
  */
 #define NUM_INIT_LISTS (3 * MAX_NUMNODES)
@@ -380,87 +375,6 @@ static void kmem_list3_init(struct kmem_list3 *parent)
 	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
 	} while (0)
 
-/*
- * struct kmem_cache
- *
- * manages a cache.
- */
-
-struct kmem_cache {
-/* 1) per-cpu data, touched during every alloc/free */
-	struct array_cache *array[NR_CPUS];
-/* 2) Cache tunables. Protected by cache_chain_mutex */
-	unsigned int batchcount;
-	unsigned int limit;
-	unsigned int shared;
-
-	unsigned int buffer_size;
-	u32 reciprocal_buffer_size;
-/* 3) touched by every alloc & free from the backend */
-
-	unsigned int flags;		/* constant flags */
-	unsigned int num;		/* # of objs per slab */
-
-/* 4) cache_grow/shrink */
-	/* order of pgs per slab (2^n) */
-	unsigned int gfporder;
-
-	/* force GFP flags, e.g. GFP_DMA */
-	gfp_t gfpflags;
-
-	size_t colour;			/* cache colouring range */
-	unsigned int colour_off;	/* colour offset */
-	struct kmem_cache *slabp_cache;
-	unsigned int slab_size;
-	unsigned int dflags;		/* dynamic flags */
-
-	/* constructor func */
-	void (*ctor)(void *obj);
-
-/* 5) cache creation/removal */
-	const char *name;
-	struct list_head next;
-
-/* 6) statistics */
-#if STATS
-	unsigned long num_active;
-	unsigned long num_allocations;
-	unsigned long high_mark;
-	unsigned long grown;
-	unsigned long reaped;
-	unsigned long errors;
-	unsigned long max_freeable;
-	unsigned long node_allocs;
-	unsigned long node_frees;
-	unsigned long node_overflow;
-	atomic_t allochit;
-	atomic_t allocmiss;
-	atomic_t freehit;
-	atomic_t freemiss;
-#endif
-#if DEBUG
-	/*
-	 * If debugging is enabled, then the allocator can add additional
-	 * fields and/or padding to every object. buffer_size contains the total
-	 * object size including these internal fields, the following two
-	 * variables contain the offset to the user object and its size.
-	 */
-	int obj_offset;
-	int obj_size;
-#endif
-	/*
-	 * We put nodelists[] at the end of kmem_cache, because we want to size
-	 * this array to nr_node_ids slots instead of MAX_NUMNODES
-	 * (see kmem_cache_init())
-	 * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of nodes.
-	 */
-	struct kmem_list3 *nodelists[MAX_NUMNODES];
-	/*
-	 * Do not add fields after nodelists[]
-	 */
-};
-
 #define CFLGS_OFF_SLAB		(0x80000000UL)
 #define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
 
@@ -898,7 +812,6 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
   */
 
 static int use_alien_caches __read_mostly = 1;
-static int numa_platform __read_mostly = 1;
 static int __init noaliencache_setup(char *s)
 {
 	use_alien_caches = 0;
@@ -1457,10 +1370,8 @@ void __init kmem_cache_init(void)
 	int order;
 	int node;
 
-	if (num_possible_nodes() == 1) {
+	if (num_possible_nodes() == 1)
 		use_alien_caches = 0;
-		numa_platform = 0;
-	}
 
 	for (i = 0; i < NUM_INIT_LISTS; i++) {
 		kmem_list3_init(&initkmem_list3[i]);
@@ -1633,20 +1544,12 @@ void __init kmem_cache_init(void)
 	}
 
 	g_cpucache_up = EARLY;
-
-	/* Annotate slab for lockdep -- annotate the malloc caches */
-	init_lock_keys();
 }
 
 void __init kmem_cache_init_late(void)
 {
 	struct kmem_cache *cachep;
 
-	/*
-	 * Interrupts are enabled now so all GFP allocations are safe.
-	 */
-	slab_gfp_mask = __GFP_BITS_MASK;
-
 	/* 6) resize the head arrays to their final sizes */
 	mutex_lock(&cache_chain_mutex);
 	list_for_each_entry(cachep, &cache_chain, next)
@@ -1657,6 +1560,9 @@ void __init kmem_cache_init_late(void)
 	/* Done! */
 	g_cpucache_up = FULL;
 
+	/* Annotate slab for lockdep -- annotate the malloc caches */
+	init_lock_keys();
+
 	/*
 	 * Register a cpu startup notifier callback that initializes
 	 * cpu_cache_get for all new cpus
@@ -1707,7 +1613,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		flags |= __GFP_RECLAIMABLE;
 
-	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
+	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
 	if (!page)
 		return NULL;
 
@@ -1720,6 +1626,16 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 	for (i = 0; i < nr_pages; i++)
 		__SetPageSlab(page + i);
+
+	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
+		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
+
+		if (cachep->ctor)
+			kmemcheck_mark_uninitialized_pages(page, nr_pages);
+		else
+			kmemcheck_mark_unallocated_pages(page, nr_pages);
+	}
+
 	return page_address(page);
 }
 
@@ -1732,6 +1648,8 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	struct page *page = virt_to_page(addr);
 	const unsigned long nr_freed = i;
 
+	kmemcheck_free_shadow(page, cachep->gfporder);
+
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		sub_zone_page_state(page_zone(page),
 				NR_SLAB_RECLAIMABLE, nr_freed);
@@ -2379,6 +2297,15 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		/* really off slab. No need for manual alignment */
 		slab_size =
 		    cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
+
+#ifdef CONFIG_PAGE_POISONING
+		/* If we're going to use the generic kernel_map_pages()
+		 * poisoning, then it's going to smash the contents of
+		 * the redzone and userword anyhow, so switch them off.
+		 */
+		if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
+			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
+#endif
 	}
 
 	cachep->colour_off = cache_line_size();
@@ -2620,7 +2547,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
 	}
 
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
-		synchronize_rcu();
+		rcu_barrier();
 
 	__kmem_cache_destroy(cachep);
 	mutex_unlock(&cache_chain_mutex);
@@ -3261,7 +3188,7 @@ retry:
 		if (local_flags & __GFP_WAIT)
 			local_irq_enable();
 		kmem_flagcheck(cache, flags);
-		obj = kmem_getpages(cache, local_flags, -1);
+		obj = kmem_getpages(cache, local_flags, numa_node_id());
 		if (local_flags & __GFP_WAIT)
 			local_irq_disable();
 		if (obj) {
@@ -3369,7 +3296,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 
-	flags &= slab_gfp_mask;
+	flags &= gfp_allowed_mask;
 
 	lockdep_trace_alloc(flags);
 
@@ -3407,6 +3334,9 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
 				 flags);
 
+	if (likely(ptr))
+		kmemcheck_slab_alloc(cachep, flags, ptr, obj_size(cachep));
+
 	if (unlikely((flags & __GFP_ZERO) && ptr))
 		memset(ptr, 0, obj_size(cachep));
 
@@ -3451,7 +3381,7 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	unsigned long save_flags;
 	void *objp;
 
-	flags &= slab_gfp_mask;
+	flags &= gfp_allowed_mask;
 
 	lockdep_trace_alloc(flags);
 
@@ -3467,6 +3397,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 				 flags);
 	prefetchw(objp);
 
+	if (likely(objp))
+		kmemcheck_slab_alloc(cachep, flags, objp, obj_size(cachep));
+
 	if (unlikely((flags & __GFP_ZERO) && objp))
 		memset(objp, 0, obj_size(cachep));
 
@@ -3583,6 +3516,8 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0));
 
+	kmemcheck_slab_free(cachep, objp, obj_size(cachep));
+
 	/*
 	 * Skip calling cache_free_alien() when the platform is not numa.
 	 * This will avoid cache misses that happen while accessing slabp (which
@@ -3590,7 +3525,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 	 * variable to skip the call, which is mostly likely to be present in
 	 * the cache.
 	 */
-	if (numa_platform && cache_free_alien(cachep, objp))
+	if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
 		return;
 
 	if (likely(ac->avail < ac->limit)) {
diff --git a/mm/slob.c b/mm/slob.c
index 12f261499925..9641da3d5e58 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -46,7 +46,7 @@
  * NUMA support in SLOB is fairly simplistic, pushing most of the real
  * logic down to the page allocator, and simply doing the node accounting
  * on the upper levels. In the event that a node id is explicitly
- * provided, alloc_pages_node() with the specified node id is used
+ * provided, alloc_pages_exact_node() with the specified node id is used
  * instead. The common case (or when the node id isn't explicitly provided)
  * will default to the current node, as per numa_node_id().
  *
@@ -133,17 +133,17 @@ static LIST_HEAD(free_slob_large);
  */
 static inline int is_slob_page(struct slob_page *sp)
 {
-	return PageSlobPage((struct page *)sp);
+	return PageSlab((struct page *)sp);
 }
 
 static inline void set_slob_page(struct slob_page *sp)
 {
-	__SetPageSlobPage((struct page *)sp);
+	__SetPageSlab((struct page *)sp);
 }
 
 static inline void clear_slob_page(struct slob_page *sp)
 {
-	__ClearPageSlobPage((struct page *)sp);
+	__ClearPageSlab((struct page *)sp);
 }
 
 static inline struct slob_page *slob_page(const void *addr)
@@ -244,7 +244,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 
 #ifdef CONFIG_NUMA
 	if (node != -1)
-		page = alloc_pages_node(node, gfp, order);
+		page = alloc_pages_exact_node(node, gfp, order);
 	else
 #endif
 		page = alloc_pages(gfp, order);
@@ -595,6 +595,8 @@ EXPORT_SYMBOL(kmem_cache_create);
 void kmem_cache_destroy(struct kmem_cache *c)
 {
 	kmemleak_free(c);
+	if (c->flags & SLAB_DESTROY_BY_RCU)
+		rcu_barrier();
 	slob_free(c, sizeof(struct kmem_cache));
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
diff --git a/mm/slub.c b/mm/slub.c
index 30354bfeb43d..b9f1491a58a1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -18,9 +18,9 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kmemtrace.h>
+#include <linux/kmemcheck.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
-#include <linux/kmemleak.h>
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
 #include <linux/debugobjects.h>
@@ -147,7 +147,7 @@
 		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE)
 
 #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA)
+		SLAB_CACHE_DMA | SLAB_NOTRACK)
 
 #ifndef ARCH_KMALLOC_MINALIGN
 #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
@@ -178,12 +178,6 @@ static enum {
 	SYSFS		/* Sysfs up */
 } slab_state = DOWN;
 
-/*
- * The slab allocator is initialized with interrupts disabled. Therefore, make
- * sure early boot allocations don't accidentally enable interrupts.
- */
-static gfp_t slab_gfp_mask __read_mostly = SLAB_GFP_BOOT_MASK;
-
 /* A list of all slab caches on the system */
 static DECLARE_RWSEM(slub_lock);
 static LIST_HEAD(slab_caches);
@@ -839,6 +833,11 @@ static inline unsigned long slabs_node(struct kmem_cache *s, int node)
 	return atomic_long_read(&n->nr_slabs);
 }
 
+static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
+{
+	return atomic_long_read(&n->nr_slabs);
+}
+
 static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
 {
 	struct kmem_cache_node *n = get_node(s, node);
@@ -1057,6 +1056,8 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize,
 
 static inline unsigned long slabs_node(struct kmem_cache *s, int node)
 							{ return 0; }
+static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
+							{ return 0; }
 static inline void inc_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
@@ -1071,6 +1072,8 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node,
 {
 	int order = oo_order(oo);
 
+	flags |= __GFP_NOTRACK;
+
 	if (node == -1)
 		return alloc_pages(flags, order);
 	else
@@ -1081,11 +1084,17 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 {
 	struct page *page;
 	struct kmem_cache_order_objects oo = s->oo;
+	gfp_t alloc_gfp;
 
 	flags |= s->allocflags;
 
-	page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
-									oo);
+	/*
+	 * Let the initial higher-order allocation fail under memory pressure
+	 * so we fall-back to the minimum order allocation.
+	 */
+	alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
+
+	page = alloc_slab_page(alloc_gfp, node, oo);
 	if (unlikely(!page)) {
 		oo = s->min;
 		/*
@@ -1098,6 +1107,24 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
 	}
+
+	if (kmemcheck_enabled
+		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS)))
+	{
+		int pages = 1 << oo_order(oo);
+
+		kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
+
+		/*
+		 * Objects from caches that have a constructor don't get
+		 * cleared when they're allocated, so we need to do it here.
+		 */
+		if (s->ctor)
+			kmemcheck_mark_uninitialized_pages(page, pages);
+		else
+			kmemcheck_mark_unallocated_pages(page, pages);
+	}
+
 	page->objects = oo_objects(oo);
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
@@ -1171,6 +1198,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 		__ClearPageSlubDebug(page);
 	}
 
+	kmemcheck_free_shadow(page, compound_order(page));
+
 	mod_zone_page_state(page_zone(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
@@ -1491,6 +1520,65 @@ static inline int node_match(struct kmem_cache_cpu *c, int node)
 	return 1;
 }
 
+static int count_free(struct page *page)
+{
+	return page->objects - page->inuse;
+}
+
+static unsigned long count_partial(struct kmem_cache_node *n,
+					int (*get_count)(struct page *))
+{
+	unsigned long flags;
+	unsigned long x = 0;
+	struct page *page;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	list_for_each_entry(page, &n->partial, lru)
+		x += get_count(page);
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	return x;
+}
+
+static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
+{
+#ifdef CONFIG_SLUB_DEBUG
+	return atomic_long_read(&n->total_objects);
+#else
+	return 0;
+#endif
+}
+
+static noinline void
+slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
+{
+	int node;
+
+	printk(KERN_WARNING
+		"SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
+		nid, gfpflags);
+	printk(KERN_WARNING "  cache: %s, object size: %d, buffer size: %d, "
+		"default order: %d, min order: %d\n", s->name, s->objsize,
+		s->size, oo_order(s->oo), oo_order(s->min));
+
+	for_each_online_node(node) {
+		struct kmem_cache_node *n = get_node(s, node);
+		unsigned long nr_slabs;
+		unsigned long nr_objs;
+		unsigned long nr_free;
+
+		if (!n)
+			continue;
+
+		nr_free  = count_partial(n, count_free);
+		nr_slabs = node_nr_slabs(n);
+		nr_objs  = node_nr_objs(n);
+
+		printk(KERN_WARNING
+			"  node %d: slabs: %ld, objs: %ld, free: %ld\n",
+			node, nr_slabs, nr_objs, nr_free);
+	}
+}
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
@@ -1572,6 +1660,8 @@ new_slab:
 		c->page = new;
 		goto load_freelist;
 	}
+	if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
+		slab_out_of_memory(s, gfpflags, node);
 	return NULL;
 debug:
 	if (!alloc_debug_processing(s, c->page, object, addr))
@@ -1601,7 +1691,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	unsigned long flags;
 	unsigned int objsize;
 
-	gfpflags &= slab_gfp_mask;
+	gfpflags &= gfp_allowed_mask;
 
 	lockdep_trace_alloc(gfpflags);
 	might_sleep_if(gfpflags & __GFP_WAIT);
@@ -1626,7 +1716,9 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	if (unlikely((gfpflags & __GFP_ZERO) && object))
 		memset(object, 0, objsize);
 
+	kmemcheck_slab_alloc(s, gfpflags, object, c->objsize);
 	kmemleak_alloc_recursive(object, objsize, 1, s->flags, gfpflags);
+
 	return object;
 }
 
@@ -1759,6 +1851,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	kmemleak_free_recursive(x, s->flags);
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
+	kmemcheck_slab_free(s, object, c->objsize);
 	debug_check_no_locks_freed(object, c->objsize);
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(object, c->objsize);
@@ -2501,6 +2594,8 @@ static inline int kmem_cache_close(struct kmem_cache *s)
  */
 void kmem_cache_destroy(struct kmem_cache *s)
 {
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		rcu_barrier();
 	down_write(&slub_lock);
 	s->refcount--;
 	if (!s->refcount) {
@@ -2610,6 +2705,7 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 	struct kmem_cache *s;
 	char *text;
 	size_t realsize;
+	unsigned long slabflags;
 
 	s = kmalloc_caches_dma[index];
 	if (s)
@@ -2631,9 +2727,18 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 			 (unsigned int)realsize);
 	s = kmalloc(kmem_size, flags & ~SLUB_DMA);
 
+	/*
+	 * Must defer sysfs creation to a workqueue because we don't know
+	 * what context we are called from. Before sysfs comes up, we don't
+	 * need to do anything because our sysfs initcall will start by
+	 * adding all existing slabs to sysfs.
+	 */
+	slabflags = SLAB_CACHE_DMA|SLAB_NOTRACK;
+	if (slab_state >= SYSFS)
+		slabflags |= __SYSFS_ADD_DEFERRED;
+
 	if (!s || !text || !kmem_cache_open(s, flags, text,
-			realsize, ARCH_KMALLOC_MINALIGN,
-			SLAB_CACHE_DMA|__SYSFS_ADD_DEFERRED, NULL)) {
+			realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) {
 		kfree(s);
 		kfree(text);
 		goto unlock_out;
@@ -2642,7 +2747,8 @@ static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
 	list_add(&s->list, &slab_caches);
 	kmalloc_caches_dma[index] = s;
 
-	schedule_work(&sysfs_add_work);
+	if (slab_state >= SYSFS)
+		schedule_work(&sysfs_add_work);
 
 unlock_out:
 	up_write(&slub_lock);
@@ -2727,13 +2833,16 @@ EXPORT_SYMBOL(__kmalloc);
 
 static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
-	struct page *page = alloc_pages_node(node, flags | __GFP_COMP,
-						get_order(size));
+	struct page *page;
+	void *ptr = NULL;
 
+	flags |= __GFP_COMP | __GFP_NOTRACK;
+	page = alloc_pages_node(node, flags, get_order(size));
 	if (page)
-		return page_address(page);
-	else
-		return NULL;
+		ptr = page_address(page);
+
+	kmemleak_alloc(ptr, size, 1, flags);
+	return ptr;
 }
 
 #ifdef CONFIG_NUMA
@@ -2818,6 +2927,7 @@ void kfree(const void *x)
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
+		kmemleak_free(x);
 		put_page(page);
 		return;
 	}
@@ -3114,10 +3224,6 @@ void __init kmem_cache_init(void)
 
 void __init kmem_cache_init_late(void)
 {
-	/*
-	 * Interrupts are enabled now so all GFP allocations are safe.
-	 */
-	slab_gfp_mask = __GFP_BITS_MASK;
 }
 
 /*
@@ -3340,20 +3446,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 }
 
 #ifdef CONFIG_SLUB_DEBUG
-static unsigned long count_partial(struct kmem_cache_node *n,
-					int (*get_count)(struct page *))
-{
-	unsigned long flags;
-	unsigned long x = 0;
-	struct page *page;
-
-	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(page, &n->partial, lru)
-		x += get_count(page);
-	spin_unlock_irqrestore(&n->list_lock, flags);
-	return x;
-}
-
 static int count_inuse(struct page *page)
 {
 	return page->inuse;
@@ -3364,11 +3456,6 @@ static int count_total(struct page *page)
 	return page->objects;
 }
 
-static int count_free(struct page *page)
-{
-	return page->objects - page->inuse;
-}
-
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {
@@ -3737,7 +3824,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 						 to_cpumask(l->cpus));
 		}
 
-		if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&
+		if (nr_online_nodes > 1 && !nodes_empty(l->nodes) &&
 				len < PAGE_SIZE - 60) {
 			len += sprintf(buf + len, " nodes=");
 			len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50,
@@ -4412,6 +4499,8 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = 'a';
 	if (s->flags & SLAB_DEBUG_FREE)
 		*p++ = 'F';
+	if (!(s->flags & SLAB_NOTRACK))
+		*p++ = 't';
 	if (p != name + 1)
 		*p++ = '-';
 	p += sprintf(p, "%07d", s->size);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 1416e7e9e02d..42cd38eba79f 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -124,7 +124,6 @@ void __delete_from_swap_cache(struct page *page)
 /**
  * add_to_swap - allocate swap space for a page
  * @page: page we want to move to swap
- * @gfp_mask: memory allocation flags
  *
  * Allocate swap space for the page and add the page to the
  * swap cache.  Caller needs to hold the page lock. 
@@ -162,11 +161,11 @@ int add_to_swap(struct page *page)
 			return 1;
 		case -EEXIST:
 			/* Raced with "speculative" read_swap_cache_async */
-			swap_free(entry);
+			swapcache_free(entry, NULL);
 			continue;
 		default:
 			/* -ENOMEM radix-tree allocation failure */
-			swap_free(entry);
+			swapcache_free(entry, NULL);
 			return 0;
 		}
 	}
@@ -188,8 +187,7 @@ void delete_from_swap_cache(struct page *page)
 	__delete_from_swap_cache(page);
 	spin_unlock_irq(&swapper_space.tree_lock);
 
-	mem_cgroup_uncharge_swapcache(page, entry);
-	swap_free(entry);
+	swapcache_free(entry, page);
 	page_cache_release(page);
 }
 
@@ -293,7 +291,10 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		/*
 		 * Swap entry may have been freed since our caller observed it.
 		 */
-		if (!swap_duplicate(entry))
+		err = swapcache_prepare(entry);
+		if (err == -EEXIST) /* seems racy */
+			continue;
+		if (err)           /* swp entry is obsolete ? */
 			break;
 
 		/*
@@ -312,12 +313,12 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			 * Initiate read into locked page and return.
 			 */
 			lru_cache_add_anon(new_page);
-			swap_readpage(NULL, new_page);
+			swap_readpage(new_page);
 			return new_page;
 		}
 		ClearPageSwapBacked(new_page);
 		__clear_page_locked(new_page);
-		swap_free(entry);
+		swapcache_free(entry, NULL);
 	} while (err != -ENOMEM);
 
 	if (new_page)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 312fafe0ab6e..8ffdc0d23c53 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -53,6 +53,59 @@ static struct swap_info_struct swap_info[MAX_SWAPFILES];
 
 static DEFINE_MUTEX(swapon_mutex);
 
+/* For reference count accounting in swap_map */
+/* enum for swap_map[] handling. internal use only */
+enum {
+	SWAP_MAP = 0,	/* ops for reference from swap users */
+	SWAP_CACHE,	/* ops for reference from swap cache */
+};
+
+static inline int swap_count(unsigned short ent)
+{
+	return ent & SWAP_COUNT_MASK;
+}
+
+static inline bool swap_has_cache(unsigned short ent)
+{
+	return !!(ent & SWAP_HAS_CACHE);
+}
+
+static inline unsigned short encode_swapmap(int count, bool has_cache)
+{
+	unsigned short ret = count;
+
+	if (has_cache)
+		return SWAP_HAS_CACHE | ret;
+	return ret;
+}
+
+/* returnes 1 if swap entry is freed */
+static int
+__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
+{
+	int type = si - swap_info;
+	swp_entry_t entry = swp_entry(type, offset);
+	struct page *page;
+	int ret = 0;
+
+	page = find_get_page(&swapper_space, entry.val);
+	if (!page)
+		return 0;
+	/*
+	 * This function is called from scan_swap_map() and it's called
+	 * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
+	 * We have to use trylock for avoiding deadlock. This is a special
+	 * case and you should use try_to_free_swap() with explicit lock_page()
+	 * in usual operations.
+	 */
+	if (trylock_page(page)) {
+		ret = try_to_free_swap(page);
+		unlock_page(page);
+	}
+	page_cache_release(page);
+	return ret;
+}
+
 /*
  * We need this because the bdev->unplug_fn can sleep and we cannot
  * hold swap_lock while calling the unplug_fn. And swap_lock
@@ -167,7 +220,8 @@ static int wait_for_discard(void *word)
 #define SWAPFILE_CLUSTER	256
 #define LATENCY_LIMIT		256
 
-static inline unsigned long scan_swap_map(struct swap_info_struct *si)
+static inline unsigned long scan_swap_map(struct swap_info_struct *si,
+					  int cache)
 {
 	unsigned long offset;
 	unsigned long scan_base;
@@ -273,6 +327,19 @@ checks:
 		goto no_page;
 	if (offset > si->highest_bit)
 		scan_base = offset = si->lowest_bit;
+
+	/* reuse swap entry of cache-only swap if not busy. */
+	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+		int swap_was_freed;
+		spin_unlock(&swap_lock);
+		swap_was_freed = __try_to_reclaim_swap(si, offset);
+		spin_lock(&swap_lock);
+		/* entry was freed successfully, try to use this again */
+		if (swap_was_freed)
+			goto checks;
+		goto scan; /* check next one */
+	}
+
 	if (si->swap_map[offset])
 		goto scan;
 
@@ -285,7 +352,10 @@ checks:
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
 	}
-	si->swap_map[offset] = 1;
+	if (cache == SWAP_CACHE) /* at usual swap-out via vmscan.c */
+		si->swap_map[offset] = encode_swapmap(0, true);
+	else /* at suspend */
+		si->swap_map[offset] = encode_swapmap(1, false);
 	si->cluster_next = offset + 1;
 	si->flags -= SWP_SCANNING;
 
@@ -351,6 +421,10 @@ scan:
 			spin_lock(&swap_lock);
 			goto checks;
 		}
+		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+			spin_lock(&swap_lock);
+			goto checks;
+		}
 		if (unlikely(--latency_ration < 0)) {
 			cond_resched();
 			latency_ration = LATENCY_LIMIT;
@@ -362,6 +436,10 @@ scan:
 			spin_lock(&swap_lock);
 			goto checks;
 		}
+		if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
+			spin_lock(&swap_lock);
+			goto checks;
+		}
 		if (unlikely(--latency_ration < 0)) {
 			cond_resched();
 			latency_ration = LATENCY_LIMIT;
@@ -401,7 +479,8 @@ swp_entry_t get_swap_page(void)
 			continue;
 
 		swap_list.next = next;
-		offset = scan_swap_map(si);
+		/* This is called for allocating swap entry for cache */
+		offset = scan_swap_map(si, SWAP_CACHE);
 		if (offset) {
 			spin_unlock(&swap_lock);
 			return swp_entry(type, offset);
@@ -415,6 +494,7 @@ noswap:
 	return (swp_entry_t) {0};
 }
 
+/* The only caller of this function is now susupend routine */
 swp_entry_t get_swap_page_of_type(int type)
 {
 	struct swap_info_struct *si;
@@ -424,7 +504,8 @@ swp_entry_t get_swap_page_of_type(int type)
 	si = swap_info + type;
 	if (si->flags & SWP_WRITEOK) {
 		nr_swap_pages--;
-		offset = scan_swap_map(si);
+		/* This is called for allocating swap entry, not cache */
+		offset = scan_swap_map(si, SWAP_MAP);
 		if (offset) {
 			spin_unlock(&swap_lock);
 			return swp_entry(type, offset);
@@ -471,26 +552,40 @@ out:
 	return NULL;
 }
 
-static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent)
+static int swap_entry_free(struct swap_info_struct *p,
+			   swp_entry_t ent, int cache)
 {
 	unsigned long offset = swp_offset(ent);
-	int count = p->swap_map[offset];
-
-	if (count < SWAP_MAP_MAX) {
-		count--;
-		p->swap_map[offset] = count;
-		if (!count) {
-			if (offset < p->lowest_bit)
-				p->lowest_bit = offset;
-			if (offset > p->highest_bit)
-				p->highest_bit = offset;
-			if (p->prio > swap_info[swap_list.next].prio)
-				swap_list.next = p - swap_info;
-			nr_swap_pages++;
-			p->inuse_pages--;
-			mem_cgroup_uncharge_swap(ent);
+	int count = swap_count(p->swap_map[offset]);
+	bool has_cache;
+
+	has_cache = swap_has_cache(p->swap_map[offset]);
+
+	if (cache == SWAP_MAP) { /* dropping usage count of swap */
+		if (count < SWAP_MAP_MAX) {
+			count--;
+			p->swap_map[offset] = encode_swapmap(count, has_cache);
 		}
+	} else { /* dropping swap cache flag */
+		VM_BUG_ON(!has_cache);
+		p->swap_map[offset] = encode_swapmap(count, false);
+
+	}
+	/* return code. */
+	count = p->swap_map[offset];
+	/* free if no reference */
+	if (!count) {
+		if (offset < p->lowest_bit)
+			p->lowest_bit = offset;
+		if (offset > p->highest_bit)
+			p->highest_bit = offset;
+		if (p->prio > swap_info[swap_list.next].prio)
+			swap_list.next = p - swap_info;
+		nr_swap_pages++;
+		p->inuse_pages--;
 	}
+	if (!swap_count(count))
+		mem_cgroup_uncharge_swap(ent);
 	return count;
 }
 
@@ -504,9 +599,33 @@ void swap_free(swp_entry_t entry)
 
 	p = swap_info_get(entry);
 	if (p) {
-		swap_entry_free(p, entry);
+		swap_entry_free(p, entry, SWAP_MAP);
+		spin_unlock(&swap_lock);
+	}
+}
+
+/*
+ * Called after dropping swapcache to decrease refcnt to swap entries.
+ */
+void swapcache_free(swp_entry_t entry, struct page *page)
+{
+	struct swap_info_struct *p;
+	int ret;
+
+	p = swap_info_get(entry);
+	if (p) {
+		ret = swap_entry_free(p, entry, SWAP_CACHE);
+		if (page) {
+			bool swapout;
+			if (ret)
+				swapout = true; /* the end of swap out */
+			else
+				swapout = false; /* no more swap users! */
+			mem_cgroup_uncharge_swapcache(page, entry, swapout);
+		}
 		spin_unlock(&swap_lock);
 	}
+	return;
 }
 
 /*
@@ -521,8 +640,7 @@ static inline int page_swapcount(struct page *page)
 	entry.val = page_private(page);
 	p = swap_info_get(entry);
 	if (p) {
-		/* Subtract the 1 for the swap cache itself */
-		count = p->swap_map[swp_offset(entry)] - 1;
+		count = swap_count(p->swap_map[swp_offset(entry)]);
 		spin_unlock(&swap_lock);
 	}
 	return count;
@@ -584,7 +702,7 @@ int free_swap_and_cache(swp_entry_t entry)
 
 	p = swap_info_get(entry);
 	if (p) {
-		if (swap_entry_free(p, entry) == 1) {
+		if (swap_entry_free(p, entry, SWAP_MAP) == SWAP_HAS_CACHE) {
 			page = find_get_page(&swapper_space, entry.val);
 			if (page && !trylock_page(page)) {
 				page_cache_release(page);
@@ -635,7 +753,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 
 		if (!bdev) {
 			if (bdev_p)
-				*bdev_p = bdget(sis->bdev->bd_dev);
+				*bdev_p = bdgrab(sis->bdev);
 
 			spin_unlock(&swap_lock);
 			return i;
@@ -647,7 +765,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 					struct swap_extent, list);
 			if (se->start_block == offset) {
 				if (bdev_p)
-					*bdev_p = bdget(sis->bdev->bd_dev);
+					*bdev_p = bdgrab(sis->bdev);
 
 				spin_unlock(&swap_lock);
 				bdput(bdev);
@@ -891,7 +1009,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
 			i = 1;
 		}
 		count = si->swap_map[i];
-		if (count && count != SWAP_MAP_BAD)
+		if (count && swap_count(count) != SWAP_MAP_BAD)
 			break;
 	}
 	return i;
@@ -995,13 +1113,13 @@ static int try_to_unuse(unsigned int type)
 		 */
 		shmem = 0;
 		swcount = *swap_map;
-		if (swcount > 1) {
+		if (swap_count(swcount)) {
 			if (start_mm == &init_mm)
 				shmem = shmem_unuse(entry, page);
 			else
 				retval = unuse_mm(start_mm, entry, page);
 		}
-		if (*swap_map > 1) {
+		if (swap_count(*swap_map)) {
 			int set_start_mm = (*swap_map >= swcount);
 			struct list_head *p = &start_mm->mmlist;
 			struct mm_struct *new_start_mm = start_mm;
@@ -1011,7 +1129,7 @@ static int try_to_unuse(unsigned int type)
 			atomic_inc(&new_start_mm->mm_users);
 			atomic_inc(&prev_mm->mm_users);
 			spin_lock(&mmlist_lock);
-			while (*swap_map > 1 && !retval && !shmem &&
+			while (swap_count(*swap_map) && !retval && !shmem &&
 					(p = p->next) != &start_mm->mmlist) {
 				mm = list_entry(p, struct mm_struct, mmlist);
 				if (!atomic_inc_not_zero(&mm->mm_users))
@@ -1023,14 +1141,16 @@ static int try_to_unuse(unsigned int type)
 				cond_resched();
 
 				swcount = *swap_map;
-				if (swcount <= 1)
+				if (!swap_count(swcount)) /* any usage ? */
 					;
 				else if (mm == &init_mm) {
 					set_start_mm = 1;
 					shmem = shmem_unuse(entry, page);
 				} else
 					retval = unuse_mm(mm, entry, page);
-				if (set_start_mm && *swap_map < swcount) {
+
+				if (set_start_mm &&
+				    swap_count(*swap_map) < swcount) {
 					mmput(new_start_mm);
 					atomic_inc(&mm->mm_users);
 					new_start_mm = mm;
@@ -1057,21 +1177,25 @@ static int try_to_unuse(unsigned int type)
 		}
 
 		/*
-		 * How could swap count reach 0x7fff when the maximum
-		 * pid is 0x7fff, and there's no way to repeat a swap
-		 * page within an mm (except in shmem, where it's the
-		 * shared object which takes the reference count)?
-		 * We believe SWAP_MAP_MAX cannot occur in Linux 2.4.
-		 *
+		 * How could swap count reach 0x7ffe ?
+		 * There's no way to repeat a swap page within an mm
+		 * (except in shmem, where it's the shared object which takes
+		 * the reference count)?
+		 * We believe SWAP_MAP_MAX cannot occur.(if occur, unsigned
+		 * short is too small....)
 		 * If that's wrong, then we should worry more about
 		 * exit_mmap() and do_munmap() cases described above:
 		 * we might be resetting SWAP_MAP_MAX too early here.
 		 * We know "Undead"s can happen, they're okay, so don't
 		 * report them; but do report if we reset SWAP_MAP_MAX.
 		 */
-		if (*swap_map == SWAP_MAP_MAX) {
+		/* We might release the lock_page() in unuse_mm(). */
+		if (!PageSwapCache(page) || page_private(page) != entry.val)
+			goto retry;
+
+		if (swap_count(*swap_map) == SWAP_MAP_MAX) {
 			spin_lock(&swap_lock);
-			*swap_map = 1;
+			*swap_map = encode_swapmap(0, true);
 			spin_unlock(&swap_lock);
 			reset_overflow = 1;
 		}
@@ -1089,7 +1213,8 @@ static int try_to_unuse(unsigned int type)
 		 * pages would be incorrect if swap supported "shared
 		 * private" pages, but they are handled by tmpfs files.
 		 */
-		if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) {
+		if (swap_count(*swap_map) &&
+		     PageDirty(page) && PageSwapCache(page)) {
 			struct writeback_control wbc = {
 				.sync_mode = WB_SYNC_NONE,
 			};
@@ -1116,6 +1241,7 @@ static int try_to_unuse(unsigned int type)
 		 * mark page dirty so shrink_page_list will preserve it.
 		 */
 		SetPageDirty(page);
+retry:
 		unlock_page(page);
 		page_cache_release(page);
 
@@ -1942,15 +2068,23 @@ void si_swapinfo(struct sysinfo *val)
  *
  * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
  * "permanent", but will be reclaimed by the next swapoff.
+ * Returns error code in following case.
+ * - success -> 0
+ * - swp_entry is invalid -> EINVAL
+ * - swp_entry is migration entry -> EINVAL
+ * - swap-cache reference is requested but there is already one. -> EEXIST
+ * - swap-cache reference is requested but the entry is not used. -> ENOENT
  */
-int swap_duplicate(swp_entry_t entry)
+static int __swap_duplicate(swp_entry_t entry, bool cache)
 {
 	struct swap_info_struct * p;
 	unsigned long offset, type;
-	int result = 0;
+	int result = -EINVAL;
+	int count;
+	bool has_cache;
 
 	if (is_migration_entry(entry))
-		return 1;
+		return -EINVAL;
 
 	type = swp_type(entry);
 	if (type >= nr_swapfiles)
@@ -1959,17 +2093,40 @@ int swap_duplicate(swp_entry_t entry)
 	offset = swp_offset(entry);
 
 	spin_lock(&swap_lock);
-	if (offset < p->max && p->swap_map[offset]) {
-		if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
-			p->swap_map[offset]++;
-			result = 1;
-		} else if (p->swap_map[offset] <= SWAP_MAP_MAX) {
+
+	if (unlikely(offset >= p->max))
+		goto unlock_out;
+
+	count = swap_count(p->swap_map[offset]);
+	has_cache = swap_has_cache(p->swap_map[offset]);
+
+	if (cache == SWAP_CACHE) { /* called for swapcache/swapin-readahead */
+
+		/* set SWAP_HAS_CACHE if there is no cache and entry is used */
+		if (!has_cache && count) {
+			p->swap_map[offset] = encode_swapmap(count, true);
+			result = 0;
+		} else if (has_cache) /* someone added cache */
+			result = -EEXIST;
+		else if (!count) /* no users */
+			result = -ENOENT;
+
+	} else if (count || has_cache) {
+		if (count < SWAP_MAP_MAX - 1) {
+			p->swap_map[offset] = encode_swapmap(count + 1,
+							     has_cache);
+			result = 0;
+		} else if (count <= SWAP_MAP_MAX) {
 			if (swap_overflow++ < 5)
-				printk(KERN_WARNING "swap_dup: swap entry overflow\n");
-			p->swap_map[offset] = SWAP_MAP_MAX;
-			result = 1;
+				printk(KERN_WARNING
+				       "swap_dup: swap entry overflow\n");
+			p->swap_map[offset] = encode_swapmap(SWAP_MAP_MAX,
+							      has_cache);
+			result = 0;
 		}
-	}
+	} else
+		result = -ENOENT; /* unused swap entry */
+unlock_out:
 	spin_unlock(&swap_lock);
 out:
 	return result;
@@ -1978,6 +2135,27 @@ bad_file:
 	printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
 	goto out;
 }
+/*
+ * increase reference count of swap entry by 1.
+ */
+void swap_duplicate(swp_entry_t entry)
+{
+	__swap_duplicate(entry, SWAP_MAP);
+}
+
+/*
+ * @entry: swap entry for which we allocate swap cache.
+ *
+ * Called when allocating swap cache for exising swap entry,
+ * This can return error codes. Returns 0 at success.
+ * -EBUSY means there is a swap cache.
+ * Note: return code is different from swap_duplicate().
+ */
+int swapcache_prepare(swp_entry_t entry)
+{
+	return __swap_duplicate(entry, SWAP_CACHE);
+}
+
 
 struct swap_info_struct *
 get_swap_info_struct(unsigned type)
@@ -2016,7 +2194,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
 		/* Don't read in free or bad pages */
 		if (!si->swap_map[toff])
 			break;
-		if (si->swap_map[toff] == SWAP_MAP_BAD)
+		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
 			break;
 	}
 	/* Count contiguous allocated slots below our target */
@@ -2024,7 +2202,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
 		/* Don't read in free or bad pages */
 		if (!si->swap_map[toff])
 			break;
-		if (si->swap_map[toff] == SWAP_MAP_BAD)
+		if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
 			break;
 	}
 	spin_unlock(&swap_lock);
diff --git a/mm/thrash.c b/mm/thrash.c
index c4c5205a9c35..2372d4ed5dd8 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -26,47 +26,45 @@ static DEFINE_SPINLOCK(swap_token_lock);
 struct mm_struct *swap_token_mm;
 static unsigned int global_faults;
 
-void grab_swap_token(void)
+void grab_swap_token(struct mm_struct *mm)
 {
 	int current_interval;
 
 	global_faults++;
 
-	current_interval = global_faults - current->mm->faultstamp;
+	current_interval = global_faults - mm->faultstamp;
 
 	if (!spin_trylock(&swap_token_lock))
 		return;
 
 	/* First come first served */
 	if (swap_token_mm == NULL) {
-		current->mm->token_priority = current->mm->token_priority + 2;
-		swap_token_mm = current->mm;
+		mm->token_priority = mm->token_priority + 2;
+		swap_token_mm = mm;
 		goto out;
 	}
 
-	if (current->mm != swap_token_mm) {
-		if (current_interval < current->mm->last_interval)
-			current->mm->token_priority++;
+	if (mm != swap_token_mm) {
+		if (current_interval < mm->last_interval)
+			mm->token_priority++;
 		else {
-			if (likely(current->mm->token_priority > 0))
-				current->mm->token_priority--;
+			if (likely(mm->token_priority > 0))
+				mm->token_priority--;
 		}
 		/* Check if we deserve the token */
-		if (current->mm->token_priority >
-				swap_token_mm->token_priority) {
-			current->mm->token_priority += 2;
-			swap_token_mm = current->mm;
+		if (mm->token_priority > swap_token_mm->token_priority) {
+			mm->token_priority += 2;
+			swap_token_mm = mm;
 		}
 	} else {
 		/* Token holder came in again! */
-		current->mm->token_priority += 2;
+		mm->token_priority += 2;
 	}
 
 out:
-	current->mm->faultstamp = global_faults;
-	current->mm->last_interval = current_interval;
+	mm->faultstamp = global_faults;
+	mm->last_interval = current_interval;
 	spin_unlock(&swap_token_lock);
-return;
 }
 
 /* Called on process exit. */
diff --git a/mm/truncate.c b/mm/truncate.c
index 12e1579f9165..ccc3ecf7cb98 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -267,8 +267,21 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 }
 EXPORT_SYMBOL(truncate_inode_pages);
 
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
-				pgoff_t start, pgoff_t end, bool be_atomic)
+/**
+ * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
+ * @mapping: the address_space which holds the pages to invalidate
+ * @start: the offset 'from' which to invalidate
+ * @end: the offset 'to' which to invalidate (inclusive)
+ *
+ * This function only removes the unlocked pages, if you want to
+ * remove all the pages of one inode, you must call truncate_inode_pages.
+ *
+ * invalidate_mapping_pages() will not block on IO activity. It will not
+ * invalidate pages which are dirty, locked, under writeback or mapped into
+ * pagetables.
+ */
+unsigned long invalidate_mapping_pages(struct address_space *mapping,
+				       pgoff_t start, pgoff_t end)
 {
 	struct pagevec pvec;
 	pgoff_t next = start;
@@ -309,30 +322,10 @@ unlock:
 				break;
 		}
 		pagevec_release(&pvec);
-		if (likely(!be_atomic))
-			cond_resched();
+		cond_resched();
 	}
 	return ret;
 }
-
-/**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
- * @start: the offset 'from' which to invalidate
- * @end: the offset 'to' which to invalidate (inclusive)
- *
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
- *
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
- */
-unsigned long invalidate_mapping_pages(struct address_space *mapping,
-				pgoff_t start, pgoff_t end)
-{
-	return __invalidate_mapping_pages(mapping, start, end, false);
-}
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
 /*
diff --git a/mm/util.c b/mm/util.c
index abc65aa7cdfc..7c35ad95f927 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -168,6 +168,10 @@ EXPORT_SYMBOL(krealloc);
  *
  * The memory of the object @p points to is zeroed before freed.
  * If @p is %NULL, kzfree() does nothing.
+ *
+ * Note: this function zeroes the whole allocated buffer which can be a good
+ * deal bigger than the requested buffer size passed to kmalloc(). So be
+ * careful when using this function in performance sensitive code.
  */
 void kzfree(const void *p)
 {
@@ -233,13 +237,21 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
  * @pages:	array that receives pointers to the pages pinned.
  *		Should be at least nr_pages long.
  *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
  * Returns number of pages pinned. This may be fewer than the number
  * requested. If nr_pages is 0 or negative, returns 0. If no pages
  * were pinned, returns -errno.
+ *
+ * get_user_pages_fast provides equivalent functionality to get_user_pages,
+ * operating on current and current->mm, with force=0 and vma=NULL. However
+ * unlike get_user_pages, it must be called without mmap_sem held.
+ *
+ * get_user_pages_fast may take mmap_sem and page table locks, so no
+ * assumptions can be made about lack of locking. get_user_pages_fast is to be
+ * implemented in a way that is advantageous (vs get_user_pages()) when the
+ * user memory area is already faulted in and present in ptes. However if the
+ * pages have to be faulted in, it may turn out to be slightly slower so
+ * callers need to carefully consider what to use. On many architectures,
+ * get_user_pages_fast simply falls back to get_user_pages.
  */
 int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 				int nr_pages, int write, struct page **pages)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 95c08a8cc2ba..dea7abd31098 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -470,8 +470,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		swp_entry_t swap = { .val = page_private(page) };
 		__delete_from_swap_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
-		mem_cgroup_uncharge_swapcache(page, swap);
-		swap_free(swap);
+		swapcache_free(swap, page);
 	} else {
 		__remove_from_page_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
@@ -514,7 +513,6 @@ int remove_mapping(struct address_space *mapping, struct page *page)
  *
  * lru_lock must not be held, interrupts must be enabled.
  */
-#ifdef CONFIG_UNEVICTABLE_LRU
 void putback_lru_page(struct page *page)
 {
 	int lru;
@@ -568,20 +566,6 @@ redo:
 	put_page(page);		/* drop ref from isolate */
 }
 
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-void putback_lru_page(struct page *page)
-{
-	int lru;
-	VM_BUG_ON(PageLRU(page));
-
-	lru = !!TestClearPageActive(page) + page_is_file_cache(page);
-	lru_cache_add_lru(page, lru);
-	put_page(page);
-}
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
-
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -593,6 +577,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
 	unsigned long nr_reclaimed = 0;
+	unsigned long vm_flags;
 
 	cond_resched();
 
@@ -643,7 +628,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 		}
 
-		referenced = page_referenced(page, 1, sc->mem_cgroup);
+		referenced = page_referenced(page, 1,
+						sc->mem_cgroup, &vm_flags);
 		/* In active use or really unfreeable?  Activate it. */
 		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
 					referenced && page_mapping_inuse(page))
@@ -851,7 +837,6 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		 */
 		ClearPageLRU(page);
 		ret = 0;
-		mem_cgroup_del_lru(page);
 	}
 
 	return ret;
@@ -899,12 +884,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		switch (__isolate_lru_page(page, mode, file)) {
 		case 0:
 			list_move(&page->lru, dst);
+			mem_cgroup_del_lru(page);
 			nr_taken++;
 			break;
 
 		case -EBUSY:
 			/* else it is being freed elsewhere */
 			list_move(&page->lru, src);
+			mem_cgroup_rotate_lru_list(page, page_lru(page));
 			continue;
 
 		default:
@@ -943,18 +930,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			/* Check that we have not crossed a zone boundary. */
 			if (unlikely(page_zone_id(cursor_page) != zone_id))
 				continue;
-			switch (__isolate_lru_page(cursor_page, mode, file)) {
-			case 0:
+			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
 				list_move(&cursor_page->lru, dst);
+				mem_cgroup_del_lru(cursor_page);
 				nr_taken++;
 				scan++;
-				break;
-
-			case -EBUSY:
-				/* else it is being freed elsewhere */
-				list_move(&cursor_page->lru, src);
-			default:
-				break;	/* ! on LRU or wrong list */
 			}
 		}
 	}
@@ -1061,6 +1041,19 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	unsigned long nr_scanned = 0;
 	unsigned long nr_reclaimed = 0;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+	int lumpy_reclaim = 0;
+
+	/*
+	 * If we need a large contiguous chunk of memory, or have
+	 * trouble getting a small set of contiguous pages, we
+	 * will reclaim both active and inactive pages.
+	 *
+	 * We use the same threshold as pageout congestion_wait below.
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		lumpy_reclaim = 1;
+	else if (sc->order && priority < DEF_PRIORITY - 2)
+		lumpy_reclaim = 1;
 
 	pagevec_init(&pvec, 1);
 
@@ -1073,19 +1066,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_freed;
 		unsigned long nr_active;
 		unsigned int count[NR_LRU_LISTS] = { 0, };
-		int mode = ISOLATE_INACTIVE;
-
-		/*
-		 * If we need a large contiguous chunk of memory, or have
-		 * trouble getting a small set of contiguous pages, we
-		 * will reclaim both active and inactive pages.
-		 *
-		 * We use the same threshold as pageout congestion_wait below.
-		 */
-		if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-			mode = ISOLATE_BOTH;
-		else if (sc->order && priority < DEF_PRIORITY - 2)
-			mode = ISOLATE_BOTH;
+		int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
 
 		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
 			     &page_list, &nr_scan, sc->order, mode,
@@ -1122,8 +1103,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 * but that should be acceptable to the caller
 		 */
 		if (nr_freed < nr_taken && !current_is_kswapd() &&
-					sc->order > PAGE_ALLOC_COSTLY_ORDER) {
-			congestion_wait(WRITE, HZ/10);
+		    lumpy_reclaim) {
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
 			 * The attempt at page out may have made some
@@ -1217,18 +1198,54 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
  * But we had to alter page->flags anyway.
  */
 
+static void move_active_pages_to_lru(struct zone *zone,
+				     struct list_head *list,
+				     enum lru_list lru)
+{
+	unsigned long pgmoved = 0;
+	struct pagevec pvec;
+	struct page *page;
+
+	pagevec_init(&pvec, 1);
+
+	while (!list_empty(list)) {
+		page = lru_to_page(list);
+		prefetchw_prev_lru_page(page, list, flags);
+
+		VM_BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+
+		VM_BUG_ON(!PageActive(page));
+		if (!is_active_lru(lru))
+			ClearPageActive(page);	/* we are de-activating */
+
+		list_move(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_add_lru_list(page, lru);
+		pgmoved++;
+
+		if (!pagevec_add(&pvec, page) || list_empty(list)) {
+			spin_unlock_irq(&zone->lru_lock);
+			if (buffer_heads_over_limit)
+				pagevec_strip(&pvec);
+			__pagevec_release(&pvec);
+			spin_lock_irq(&zone->lru_lock);
+		}
+	}
+	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+	if (!is_active_lru(lru))
+		__count_vm_events(PGDEACTIVATE, pgmoved);
+}
 
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			struct scan_control *sc, int priority, int file)
 {
 	unsigned long pgmoved;
-	int pgdeactivate = 0;
 	unsigned long pgscanned;
+	unsigned long vm_flags;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
+	LIST_HEAD(l_active);
 	LIST_HEAD(l_inactive);
 	struct page *page;
-	struct pagevec pvec;
-	enum lru_list lru;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	lru_add_drain();
@@ -1245,13 +1262,14 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	}
 	reclaim_stat->recent_scanned[!!file] += pgmoved;
 
+	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	if (file)
 		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
 	else
 		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
-	pgmoved = 0;
+	pgmoved = 0;  /* count referenced (mapping) mapped pages */
 	while (!list_empty(&l_hold)) {
 		cond_resched();
 		page = lru_to_page(&l_hold);
@@ -1264,58 +1282,44 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 
 		/* page_referenced clears PageReferenced */
 		if (page_mapping_inuse(page) &&
-		    page_referenced(page, 0, sc->mem_cgroup))
+		    page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
 			pgmoved++;
+			/*
+			 * Identify referenced, file-backed active pages and
+			 * give them one more trip around the active list. So
+			 * that executable code get better chances to stay in
+			 * memory under moderate memory pressure.  Anon pages
+			 * are not likely to be evicted by use-once streaming
+			 * IO, plus JVM can create lots of anon VM_EXEC pages,
+			 * so we ignore them here.
+			 */
+			if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+				list_add(&page->lru, &l_active);
+				continue;
+			}
+		}
 
 		list_add(&page->lru, &l_inactive);
 	}
 
 	/*
-	 * Move the pages to the [file or anon] inactive list.
+	 * Move pages back to the lru list.
 	 */
-	pagevec_init(&pvec, 1);
-	lru = LRU_BASE + file * LRU_FILE;
-
 	spin_lock_irq(&zone->lru_lock);
 	/*
-	 * Count referenced pages from currently used mappings as
-	 * rotated, even though they are moved to the inactive list.
-	 * This helps balance scan pressure between file and anonymous
-	 * pages in get_scan_ratio.
+	 * Count referenced pages from currently used mappings as rotated,
+	 * even though only some of them are actually re-activated.  This
+	 * helps balance scan pressure between file and anonymous pages in
+	 * get_scan_ratio.
 	 */
 	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
-	pgmoved = 0;
-	while (!list_empty(&l_inactive)) {
-		page = lru_to_page(&l_inactive);
-		prefetchw_prev_lru_page(page, &l_inactive, flags);
-		VM_BUG_ON(PageLRU(page));
-		SetPageLRU(page);
-		VM_BUG_ON(!PageActive(page));
-		ClearPageActive(page);
+	move_active_pages_to_lru(zone, &l_active,
+						LRU_ACTIVE + file * LRU_FILE);
+	move_active_pages_to_lru(zone, &l_inactive,
+						LRU_BASE   + file * LRU_FILE);
 
-		list_move(&page->lru, &zone->lru[lru].list);
-		mem_cgroup_add_lru_list(page, lru);
-		pgmoved++;
-		if (!pagevec_add(&pvec, page)) {
-			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-			spin_unlock_irq(&zone->lru_lock);
-			pgdeactivate += pgmoved;
-			pgmoved = 0;
-			if (buffer_heads_over_limit)
-				pagevec_strip(&pvec);
-			__pagevec_release(&pvec);
-			spin_lock_irq(&zone->lru_lock);
-		}
-	}
-	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-	pgdeactivate += pgmoved;
-	__count_zone_vm_events(PGREFILL, zone, pgscanned);
-	__count_vm_events(PGDEACTIVATE, pgdeactivate);
 	spin_unlock_irq(&zone->lru_lock);
-	if (buffer_heads_over_limit)
-		pagevec_strip(&pvec);
-	pagevec_release(&pvec);
 }
 
 static int inactive_anon_is_low_global(struct zone *zone)
@@ -1350,12 +1354,48 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
 	return low;
 }
 
+static int inactive_file_is_low_global(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_FILE);
+	inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+	return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc:   scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+	int low;
+
+	if (scanning_global_lru(sc))
+		low = inactive_file_is_low_global(zone);
+	else
+		low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+	return low;
+}
+
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
 	int file = is_file_lru(lru);
 
-	if (lru == LRU_ACTIVE_FILE) {
+	if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
@@ -1384,13 +1424,6 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long ap, fp;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
-	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || (nr_swap_pages <= 0)) {
-		percent[0] = 0;
-		percent[1] = 100;
-		return;
-	}
-
 	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
 		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
 	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
@@ -1400,7 +1433,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 		free  = zone_page_state(zone, NR_FREE_PAGES);
 		/* If we have very few page cache pages,
 		   force-scan anon pages. */
-		if (unlikely(file + free <= zone->pages_high)) {
+		if (unlikely(file + free <= high_wmark_pages(zone))) {
 			percent[0] = 100;
 			percent[1] = 0;
 			return;
@@ -1455,6 +1488,26 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	percent[1] = 100 - percent[0];
 }
 
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+				       unsigned long *nr_saved_scan,
+				       unsigned long swap_cluster_max)
+{
+	unsigned long nr;
+
+	*nr_saved_scan += nr_to_scan;
+	nr = *nr_saved_scan;
+
+	if (nr >= swap_cluster_max)
+		*nr_saved_scan = 0;
+	else
+		nr = 0;
+
+	return nr;
+}
 
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
@@ -1468,26 +1521,30 @@ static void shrink_zone(int priority, struct zone *zone,
 	enum lru_list l;
 	unsigned long nr_reclaimed = sc->nr_reclaimed;
 	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	int noswap = 0;
 
-	get_scan_ratio(zone, sc, percent);
+	/* If we have no swap space, do not bother scanning anon pages. */
+	if (!sc->may_swap || (nr_swap_pages <= 0)) {
+		noswap = 1;
+		percent[0] = 0;
+		percent[1] = 100;
+	} else
+		get_scan_ratio(zone, sc, percent);
 
 	for_each_evictable_lru(l) {
 		int file = is_file_lru(l);
 		unsigned long scan;
 
 		scan = zone_nr_pages(zone, sc, l);
-		if (priority) {
+		if (priority || noswap) {
 			scan >>= priority;
 			scan = (scan * percent[file]) / 100;
 		}
-		if (scanning_global_lru(sc)) {
-			zone->lru[l].nr_scan += scan;
-			nr[l] = zone->lru[l].nr_scan;
-			if (nr[l] >= swap_cluster_max)
-				zone->lru[l].nr_scan = 0;
-			else
-				nr[l] = 0;
-		} else
+		if (scanning_global_lru(sc))
+			nr[l] = nr_scan_try_batch(scan,
+						  &zone->lru[l].nr_saved_scan,
+						  swap_cluster_max);
+		else
 			nr[l] = scan;
 	}
 
@@ -1521,7 +1578,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_anon_is_low(zone, sc))
+	if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0)
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
 	throttle_vm_writeout(sc->gfp_mask);
@@ -1532,11 +1589,13 @@ static void shrink_zone(int priority, struct zone *zone,
  * try to reclaim pages from zones which will satisfy the caller's allocation
  * request.
  *
- * We reclaim from a zone even if that zone is over pages_high.  Because:
+ * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
+ * Because:
  * a) The caller may be trying to free *extra* pages to satisfy a higher-order
  *    allocation or
- * b) The zones may be over pages_high but they must go *over* pages_high to
- *    satisfy the `incremental min' zone defense algorithm.
+ * b) The target zone may be at high_wmark_pages(zone) but the lower zones
+ *    must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
+ *    zone defense algorithm.
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
@@ -1662,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scanning_global_lru(sc))
@@ -1742,7 +1801,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at pages_high.
+ * they are all at high_wmark_pages(zone).
  *
  * Returns the number of pages which were actually freed.
  *
@@ -1755,11 +1814,11 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
  * the zone for when the problem goes away.
  *
  * kswapd scans the zones in the highmem->normal->dma direction.  It skips
- * zones which have free_pages > pages_high, but once a zone is found to have
- * free_pages <= pages_high, we scan that zone and the lower zones regardless
- * of the number of free pages in the lower zones.  This interoperates with
- * the page allocator fallback scheme to ensure that aging of pages is balanced
- * across the zones.
+ * zones which have free_pages > high_wmark_pages(zone), but once a zone is
+ * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
+ * lower zones regardless of the number of free pages in the lower zones. This
+ * interoperates with the page allocator fallback scheme to ensure that aging
+ * of pages is balanced across the zones.
  */
 static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 {
@@ -1780,7 +1839,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	};
 	/*
 	 * temp_priority is used to remember the scanning priority at which
-	 * this zone was successfully refilled to free_pages == pages_high.
+	 * this zone was successfully refilled to
+	 * free_pages == high_wmark_pages(zone).
 	 */
 	int temp_priority[MAX_NR_ZONES];
 
@@ -1825,8 +1885,8 @@ loop_again:
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
-			if (!zone_watermark_ok(zone, order, zone->pages_high,
-					       0, 0)) {
+			if (!zone_watermark_ok(zone, order,
+					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
 			}
@@ -1860,8 +1920,8 @@ loop_again:
 					priority != DEF_PRIORITY)
 				continue;
 
-			if (!zone_watermark_ok(zone, order, zone->pages_high,
-					       end_zone, 0))
+			if (!zone_watermark_ok(zone, order,
+					high_wmark_pages(zone), end_zone, 0))
 				all_zones_ok = 0;
 			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
@@ -1870,8 +1930,8 @@ loop_again:
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
 			 */
-			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
-						end_zone, 0))
+			if (!zone_watermark_ok(zone, order,
+					8*high_wmark_pages(zone), end_zone, 0))
 				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
@@ -1900,7 +1960,7 @@ loop_again:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -2037,7 +2097,7 @@ void wakeup_kswapd(struct zone *zone, int order)
 		return;
 
 	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
+	if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 		return;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
@@ -2084,11 +2144,11 @@ static void shrink_all_zones(unsigned long nr_pages, int prio,
 						l == LRU_ACTIVE_FILE))
 				continue;
 
-			zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
-			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+			zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
+			if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
 				unsigned long nr_to_scan;
 
-				zone->lru[l].nr_scan = 0;
+				zone->lru[l].nr_saved_scan = 0;
 				nr_to_scan = min(nr_pages, lru_pages);
 				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
@@ -2173,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(WRITE, HZ / 10);
+				congestion_wait(BLK_RW_ASYNC, HZ / 10);
 		}
 	}
 
@@ -2290,6 +2350,48 @@ int sysctl_min_unmapped_ratio = 1;
  */
 int sysctl_min_slab_ratio = 5;
 
+static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+{
+	unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
+	unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
+		zone_page_state(zone, NR_ACTIVE_FILE);
+
+	/*
+	 * It's possible for there to be more file mapped pages than
+	 * accounted for by the pages on the file LRU lists because
+	 * tmpfs pages accounted for as ANON can also be FILE_MAPPED
+	 */
+	return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
+}
+
+/* Work out how many page cache pages we can reclaim in this reclaim_mode */
+static long zone_pagecache_reclaimable(struct zone *zone)
+{
+	long nr_pagecache_reclaimable;
+	long delta = 0;
+
+	/*
+	 * If RECLAIM_SWAP is set, then all file pages are considered
+	 * potentially reclaimable. Otherwise, we have to worry about
+	 * pages like swapcache and zone_unmapped_file_pages() provides
+	 * a better estimate
+	 */
+	if (zone_reclaim_mode & RECLAIM_SWAP)
+		nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+	else
+		nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+
+	/* If we can't clean pages, remove dirty pages from consideration */
+	if (!(zone_reclaim_mode & RECLAIM_WRITE))
+		delta += zone_page_state(zone, NR_FILE_DIRTY);
+
+	/* Watch for any possible underflows due to delta */
+	if (unlikely(delta > nr_pagecache_reclaimable))
+		delta = nr_pagecache_reclaimable;
+
+	return nr_pagecache_reclaimable - delta;
+}
+
 /*
  * Try to free up some pages from this zone through reclaim.
  */
@@ -2324,9 +2426,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	if (zone_page_state(zone, NR_FILE_PAGES) -
-		zone_page_state(zone, NR_FILE_MAPPED) >
-		zone->min_unmapped_pages) {
+	if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
 		/*
 		 * Free memory by calling shrink zone with increasing
 		 * priorities until we have enough memory freed.
@@ -2384,20 +2484,18 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * if less than a specified percentage of the zone is used by
 	 * unmapped file backed pages.
 	 */
-	if (zone_page_state(zone, NR_FILE_PAGES) -
-	    zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
-	    && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
-			<= zone->min_slab_pages)
-		return 0;
+	if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
+	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
+		return ZONE_RECLAIM_FULL;
 
 	if (zone_is_all_unreclaimable(zone))
-		return 0;
+		return ZONE_RECLAIM_FULL;
 
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
 	if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
-			return 0;
+		return ZONE_RECLAIM_NOSCAN;
 
 	/*
 	 * Only run zone reclaim on the local zone or on zones that do not
@@ -2407,18 +2505,21 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 */
 	node_id = zone_to_nid(zone);
 	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
-		return 0;
+		return ZONE_RECLAIM_NOSCAN;
 
 	if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
-		return 0;
+		return ZONE_RECLAIM_NOSCAN;
+
 	ret = __zone_reclaim(zone, gfp_mask, order);
 	zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
 
+	if (!ret)
+		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
+
 	return ret;
 }
 #endif
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * page_evictable - test whether a page is evictable
  * @page: the page to test
@@ -2665,4 +2766,3 @@ void scan_unevictable_unregister_node(struct node *node)
 	sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
 }
 
-#endif
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 74d66dba0cbe..138bed53706e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -629,10 +629,8 @@ static const char * const vmstat_text[] = {
 	"nr_active_anon",
 	"nr_inactive_file",
 	"nr_active_file",
-#ifdef CONFIG_UNEVICTABLE_LRU
 	"nr_unevictable",
 	"nr_mlock",
-#endif
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
@@ -675,6 +673,9 @@ static const char * const vmstat_text[] = {
 	TEXTS_FOR_ZONES("pgscan_kswapd")
 	TEXTS_FOR_ZONES("pgscan_direct")
 
+#ifdef CONFIG_NUMA
+	"zone_reclaim_failed",
+#endif
 	"pginodesteal",
 	"slabs_scanned",
 	"kswapd_steal",
@@ -687,7 +688,6 @@ static const char * const vmstat_text[] = {
 	"htlb_buddy_alloc_success",
 	"htlb_buddy_alloc_fail",
 #endif
-#ifdef CONFIG_UNEVICTABLE_LRU
 	"unevictable_pgs_culled",
 	"unevictable_pgs_scanned",
 	"unevictable_pgs_rescued",
@@ -697,7 +697,6 @@ static const char * const vmstat_text[] = {
 	"unevictable_pgs_stranded",
 	"unevictable_pgs_mlockfreed",
 #endif
-#endif
 };
 
 static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
@@ -710,18 +709,14 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        min      %lu"
 		   "\n        low      %lu"
 		   "\n        high     %lu"
-		   "\n        scanned  %lu (aa: %lu ia: %lu af: %lu if: %lu)"
+		   "\n        scanned  %lu"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
 		   zone_page_state(zone, NR_FREE_PAGES),
-		   zone->pages_min,
-		   zone->pages_low,
-		   zone->pages_high,
+		   min_wmark_pages(zone),
+		   low_wmark_pages(zone),
+		   high_wmark_pages(zone),
 		   zone->pages_scanned,
-		   zone->lru[LRU_ACTIVE_ANON].nr_scan,
-		   zone->lru[LRU_INACTIVE_ANON].nr_scan,
-		   zone->lru[LRU_ACTIVE_FILE].nr_scan,
-		   zone->lru[LRU_INACTIVE_FILE].nr_scan,
 		   zone->spanned_pages,
 		   zone->present_pages);